Computational Models of Discourse: Lexical Chains; Centering Theory - - PowerPoint PPT Presentation

Computational Models of Discourse: Lexical Chains; Centering Theory

Caroline Sporleder

Universit¨ at des Saarlandes

Sommersemester 2009 06.05.2009

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Lexical Chains

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Lexical Chains: Example

The spiders, it seems, enter comas to survive for hours underwater, according to a new study. The unexpected discovery was made during experiments intended to find out exactly how long spiders can survive underwater – a number of spiders and insects have long been known to be resistant to drowning. In particular, researchers wanted to determine whether spiders in flood-prone marshes had evolved to survive longer underwater than forest-dwelling spiders can. Scientists at the University of Rennes in France collected three species of wolf spider – two from salt marshes, one from a forest. The team immersed 120 females of each species in seawater, jostling the spiders with brushes every two hours to see if they responded. After the ”drownings,” the researchers, hoping to weigh the spiders later, left them out to dry. That’s when things began to get weird. Hours later, the spiders began twitching and were soon back on their eight feet. ”This is the first time we know of arthropods returning to life from comas after submersion,” said lead researcher Julien P´ etillon, an arachnologist now at Ghent University in Belgium. The spiders’ survival trick depends on a switch to metabolic processes (the processes that provide energy for vital functions in the body) that do not require air, the researchers speculate.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Lexical Chains: Example

The spiders, it seems, enter comas to survive for hours underwater, according to a new study. The unexpected discovery was made during experiments intended to find out exactly how long spiders can survive underwater – a number of spiders and insects have long been known to be resistant to drowning. In particular, researchers wanted to determine whether spiders in flood-prone marshes had evolved to survive longer underwater than forest-dwelling spiders can. Scientists at the University of Rennes in France collected three species of wolf spider – two from salt marshes, one from a forest. The team immersed 120 females of each species in seawater, jostling the spiders with brushes every two hours to see if they responded. After the ”drownings,” the researchers, hoping to weigh the spiders later, left them out to dry. That’s when things began to get weird. Hours later, the spiders began twitching and were soon back on their eight feet. ”This is the first time we know of arthropods returning to life from comas after submersion,” said lead researcher Julien P´ etillon, an arachnologist now at Ghent University in Belgium. The spiders’ survival trick depends on a switch to metabolic processes (the processes that provide energy for vital functions in the body) that do not require air, the researchers speculate.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Properties of Lexical Chains

Lexical chains relate to the topics of a discourse can have different start and end points (sub-topic boundaries) can have different lengths (weak and strong chains) a given word can participate in several chains which word a chain participates in is context-dependent (word-sense disambiguation, anaphora resolution, aspects of meaning that are important in the context) ideally multi-word expressions should also be treated as single units for chain computation chain structure leaves room for interpretation

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Applications for Lexical Chains

word sense disambiguation real-word spelling error detection detection of non-literal language word prediction topic segmentation text categorisation topic detection and tracking text summarisation hypertext construction . . . ??? ⇒ lexial chains are relatively easy to compute and a good model for certain aspects of shallow text structure (esp. topic structure)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Types of spelling errors syntactic errors (The students are doing there homework.) semantic errors / malapropisms (He spent his summer travelling around the word.) structural errors (I need three ingredients: red wine, sugar, cinamon, and cloves.) pragmatic errors (He studies at the University of Toronto on England.)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Types of spelling errors syntactic errors (The students are doing there homework.) semantic errors / malapropisms (He spent his summer travelling around the word.) structural errors (I need three ingredients: red wine, sugar, cinamon, and cloves.) pragmatic errors (He studies at the University of Toronto on England.) Error detection for errors that are not real words: dictionary look-up for errors that are real words: much more difficult; need to take into account context

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Idea: content words that do not fit in any lexical chain with their context are suspicious if such a word is orthographically close to a word that would fit in a chain, then the orignal word is likely to be an error

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Idea: content words that do not fit in any lexical chain with their context are suspicious if such a word is orthographically close to a word that would fit in a chain, then the orignal word is likely to be an error Example: Peter spent the summer travelling around the word. He visited Aus- tralia, then Africa, and finally Europe.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Idea: content words that do not fit in any lexical chain with their context are suspicious if such a word is orthographically close to a word that would fit in a chain, then the orignal word is likely to be an error Example: Peter spent the summer travelling around the word. He visited Aus- tralia, then Africa, and finally Europe. compute chains

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Idea: content words that do not fit in any lexical chain with their context are suspicious if such a word is orthographically close to a word that would fit in a chain, then the orignal word is likely to be an error Example: Peter spent the summer travelling around the word. He visited Aus- tralia, then Africa, and finally Europe. compute chains “word” doesn’t fit anywhere

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Idea: content words that do not fit in any lexical chain with their context are suspicious if such a word is orthographically close to a word that would fit in a chain, then the orignal word is likely to be an error Example: Peter spent the summer travelling around the word. He visited Aus- tralia, then Africa, and finally Europe. compute chains “word” doesn’t fit anywhere

• rthographically close words are: “work” and “world”

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Idea: content words that do not fit in any lexical chain with their context are suspicious if such a word is orthographically close to a word that would fit in a chain, then the orignal word is likely to be an error Example: Peter spent the summer travelling around the word. He visited Aus- tralia, then Africa, and finally Europe. compute chains “word” doesn’t fit anywhere

• rthographically close words are: “work” and “world”;

“world” does fit in the chain ⇒ suggest “world” as a correction of “word”

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection (Hirst & St-Onge, 1995)

Modelling chains are computed using WordNet (extra strong, strong, medium strong relations) string transformations to find orthographically close words (letter deletion, insertion, transposition, replacement, insertion

• f a space or hyphen)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection: Experiments

Data: errors created automatically by applying string transformations to WSJ text (replace one word in 200) Examples: “Much of that data, he notes, is available toady electronically.” [→ “today”] “Among the largest OTC issues, Farmers Group, which expects B.A.T. Industries to launch a hostile tenter offer for it, jumped to 62 yesterday.” [→ “tender”]

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection: Results and Error Analysis

False Positive Among the largest OTC issues, Farmers Group, which expects B.A.T. Industries to launch a hostile tenter [=tender] offer for it, jumped to 62 yesterday. “tenter” was placed in a chain: tenter isa framework/frame includes handbarrow has part handle/grip/hold includes stock ⇒ wrong WSD of “stock” (only “tender” could have disambiguated)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection: Results and Error Analysis

Potential False Negative QVC Network, a 24-hour home television shopping issue, said yesterday it expects fiscal 1989 sales of $170 million to $200

• million. . .

“television” doesn’t fit any chain but also has no variants which fit thus it’s not flagged

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection: Results and Error Analysis

False Negative And while institutions until the past month or so stayed away from the smallest issues for fear they would get stuck in an illiquid stock, . . . “fear” doesn’t fit any chain

• rthographically close words: “gear”, “pear”, “year”

for all variants chains were found (e.g., “pear”-”Lotus”) “fear” was wrongly flagged as a potential error

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection: Results and Error Analysis

words in corpus 322,645 number of words in chains 109,407 number of non-malapropisms 107,998 malapropsims 1,409 atomic chains 8,014 atomic chains that contained malapropisms 442 atomic chain that did not contain malapropisms 7,572 performance factor 4.47 number of potential errors flagged 3,167 true alarms 397 false alarms 2,770 performance factor 2.46 performance factor overall 11.0 number of perfectly detected and corrected malapropisms 349 malapropisms were 4.47 times more likely to be placed in an atomic chain than non-malapropisms malapropisms in atomic chains were 2.46 times more likely to result in alarms than non-malapropisms in atomic chains in general malapropisms were 11 times more likely to be flagged as potential errors than other words

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Malapropism Detection: Results and Error Analysis

. . . or in other words error detection precision: 12.54% error detection recall: 28.18% error detection f-score: 17.36% correction accuracy for correctly detected errors: 87%

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Another Application: Idiom Detection

Problem: spill the beans (≈ reveal a secret) Scott then published a book entitled Off Whitehall, which supposedly spilled the beans on the Blair/Brown feud. spill the beans Somehow I always end up spilling the beans all over the floor and looking foolish when the clerk comes to sweep them up.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Another Application: Idiom Detection

Problem: spill the beans (≈ reveal a secret) Scott then published a book entitled Off Whitehall, which supposedly spilled the beans on the Blair/Brown feud. spill the beans Somehow I always end up spilling the beans all over the floor and looking foolish when the clerk comes to sweep them up. NLP systems need to be able to recognise idioms to assign correct analyses

• ften an expression can have literal as well as non-literal

meaning ⇒ need to disambiguate in context

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Another Application: Idiom Detection

Possible solution: . . . could label a lot of training data, define a features set for the task and then use supervised machine learning to train a classifier But training data is expensive to label.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Another Application: Idiom Detection

Possible solution: . . . could label a lot of training data, define a features set for the task and then use supervised machine learning to train a classifier But training data is expensive to label. An unsupervised approach: check whether component words of the idiom (e.g., “spill” or “bean”) occur in a (non-atomic) lexical chain if no lexical chain can be found in which the idiom participates predict non-literal usage

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Idiom Detection: Examples

spill the beans Somehow I always end up spilling the beans all over the floor and looking foolish when the clerk comes to sweep them up. spill the beans (≈ reveal a secret) Scott then published a book entitled Off Whitehall, which supposedly spilled the beans on the Blair/Brown feud.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Idiom Detection: Examples

spill the beans Somehow I always end up spilling the beans all over the floor and looking foolish when the clerk comes to sweep them up. spill the beans (≈ reveal a secret) Scott then published a book entitled Off Whitehall, which supposedly spilled the beans on the Blair/Brown feud.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

What semantic relations do we need to model?

play with fire Grilling outdoors is much more than just another dry-heat cooking

• method. It’s the chance to play with fire, satisfying a primal urge

to stir around in coals. drop the ball When Rooney collided with the goalkeeper, causing him to drop the ball, Kevin Campbell followed in.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

What semantic relations do we need to model?

play with fire Grilling outdoors is much more than just another dry-heat cooking

• method. It’s the chance to play with fire, satisfying a primal urge

to stir around in coals. drop the ball When Rooney collided with the goalkeeper, causing him to drop the ball, Kevin Campbell followed in.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

What semantic relations do we need to model?

play with fire Grilling outdoors is much more than just another dry-heat cooking

• method. It’s the chance to play with fire, satisfying a primal urge

to stir around in coals. drop the ball When Rooney collided with the goalkeeper, causing him to drop the ball, Kevin Campbell followed in.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

What semantic relations do we need to model?

Relations found: relations between non-nouns (“spill” – “sweep up”) relations across parts-of-speech (“cooking” – “fire”) ’fuzzy’ relations (“fire” – “coals”) world knowledge (“Wayne Rooney” – “ball”)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

What semantic relations do we need to model?

Relations found: relations between non-nouns (“spill” – “sweep up”) relations across parts-of-speech (“cooking” – “fire”) ’fuzzy’ relations (“fire” – “coals”) world knowledge (“Wayne Rooney” – “ball”) Relatedness measure: WordNet-based measures not suitable compiled corpora smallish and out-of-date instead compute similarity from web counts

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Web-based Relatedness Measure

Normalised Google Distance (NGD, Cilibrasi & Vitanyi 2007) NGD(x, y) = max{log f (x), log f (y)} − log f (x, y) log M − min{log f (x), log f (y)} (1) for two terms “x” and “y”, where M is the number of indexed pages. M is estimated by querying for “the” Yahoo rather than Google (more stable counts) query for all combinations of word forms

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Modelling Cohesion

Lexical Chains

• ne free parameter: relatedness threshold

⇒ need annotated data to optimise! performance very sensitive to parameter and chaining algorithm

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Modelling Cohesion

Lexical Chains

• ne free parameter: relatedness threshold

⇒ need annotated data to optimise! performance very sensitive to parameter and chaining algorithm Cohesion Graph model cohesion as a graph structure: nodes are content words, edges encode degree of relatedness between pairs of words compute how average relatedness changes if idiom is excluded from the graph: if it increases predict non-literal usage

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Data

17 idioms (mainly V+NP and V+PP) with literal and non-literal sense

• ccurrences extracted from a Gigaword corpus (3964

instances) five paragraphs context manually labelled as “literal” (862 instances) or “non-literal” (3102 instances)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Data

expression literal non-literal all back the wrong horse 25 25 bite off more than one can chew 2 142 144 bite one’s tongue 16 150 166 blow one’s own trumpet 9 9 bounce off the wall* 39 7 46 break the ice 20 521 541 drop the ball* 688 215 903 get one’s feet wet 17 140 157 pass the buck 7 255 262 play with fire 34 532 566 pull the trigger* 11 4 15 rock the boat 8 470 478 set in stone 9 272 281 spill the beans 3 172 175 sweep under the carpet 9 9 swim against the tide 1 125 126 tear one’s hair out 7 54 61 all 862 3102 3964

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Results

BMaj BRep Graph LCd LCo Super Acc 78.25 79.06 79.61 80.50 80.42 95.69

• lit. Prec
• 70.00

52.21 62.26 53.89 84.62

• lit. Rec
• 5.96

67.87 26.21 69.03 96.45

• lit. Fβ=1
• 10.98

59.02 36.90 60.53 90.15 BMaj: majority baseline, i.e., “non-literal” BRep: predict “literal” if an idiom component word is repeated in the context Graph: cohesion graph LCd: lexical chains optimised on development set LCo: lexical chains optimised globally by oracle (upper bound for lexical chains) Super: supervised classifier (k-nn) using word overlap (leave-one-out)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Limitations of the Cohesion-Based Approach

Literal Use without Lexical Chain Chinamasa compared McGown’s attitude to morphine to a child’s attitude to playing with fire – a lack of concern over the risks involved. Non-Literal Use with Lexical Chain Saying that the Americans were ”playing with fire” the official press speculated that the ”gunpowder barrel” which is Taiwan might well ”explode” if Washington and Taipei do not put a stop to their ”incendiary gesticulations.” ⇒ Both cases are relatively rare

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering Theory

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Referring Expressions: Terminology

Discourse model a representation of discourse meaning discourse entities (usually realised by NPs) properties of the discourse entities relations between discourse entities

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Referring Expressions: Terminology

Discourse model a representation of discourse meaning discourse entities (usually realised by NPs) properties of the discourse entities relations between discourse entities Referring Expression an expression that a speaker uses to refer to an entity. Referent the entity which is referred to by the referring expression. Reference the process in which the speaker uses a referring expression to refer to a discourse entity.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse Model and Reference

Dynamics of the discourse model referring expressions change the discourse model introduction of new discourse entities creation of links to “old” entities

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse model and Reference

Reference and linguistic form The linguistic form reflects the current state of the discourse context.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse model and Reference

Reference and linguistic form The linguistic form reflects the current state of the discourse context. Typically: new discourse entities are introduced by indefinite NPs

• ld discourse are referred to with definite NPs or pronouns

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse model and Reference

Reference and linguistic form The linguistic form reflects the current state of the discourse context. Typically: new discourse entities are introduced by indefinite NPs

• ld discourse are referred to with definite NPs or pronouns

⇒ I saw a cat. The cat/It was black.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse model and Reference

Reference and linguistic form The linguistic form reflects the current state of the discourse context. Typically: new discourse entities are introduced by indefinite NPs

• ld discourse are referred to with definite NPs or pronouns

⇒ I saw a cat. The cat/It was black. But: Peter went over to the house. The door was wide open. He is going to the States for a year. (A to B when C walks by)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering Theory (Grosz, Joshi, Weinstein, 1995)

Aim: Modelling the local coherence of a discourse segment? Why are some texts perceived as more coherent than others?

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering Theory (Grosz, Joshi, Weinstein, 1995)

Aim: Modelling the local coherence of a discourse segment? Why are some texts perceived as more coherent than others? Hypothesis: different types of referring expressions are associated with different inference loads badly chosen referring expressions lead to a high inference load ⇒ the discourse is perceived as incoherent

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. It was a store John had frequented for many years.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. It was a store John had frequented for many years. He was excited that he could finally buy a piano.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. It was a store John had frequented for many years. He was excited that he could finally buy a piano. It was closing just as John arrived.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. It was a store John had frequented for many years. He was excited that he could finally buy a piano. It was closing just as John arrived.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. It was a store John had frequented for many years. He was excited that he could finally buy a piano. It was closing just as John arrived.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. He had frequented the store for many years.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. He had frequented the store for many years. He was excited that he could finally buy a piano.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. He had frequented the store for many years. He was excited that he could finally buy a piano. He arrived just as the store was closing for the day.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. He had frequented the store for many years. He was excited that he could finally buy a piano. He arrived just as the store was closing for the day. ⇒ coherence has something to do with local focus (attentional state)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Differences in Coherence: Example

John went to his favorite music store to buy a piano. He had frequented the store for many years. He was excited that he could finally buy a piano. He arrived just as the store was closing for the day. ⇒ coherence has something to do with local focus (attentional state) ⇒ Too many focus shifts make a text incoherent (cognitive processing of the text becomes more difficult)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 He was sick and furious at being woken up so early. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 He was sick and furious at being woken up so early. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 He was sick and furious at being woken up so early.

“he” in (5)=Tony

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 He was sick and furious at being woken up so early.

“he” in (5)=Tony Discourse is perceived as incoherent because pronoun is supposed to refer to focal entity (=Terry). The fact that it refers to Tony here leads to a higher inference load.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 Tony was sick and furious at being woken up so early. 6 He told Terry to get lost and hung up. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 Tony was sick and furious at being woken up so early. 6 He told Terry to get lost and hung up. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 Tony was sick and furious at being woken up so early. 6 He told Terry to get lost and hung up. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 Tony was sick and furious at being woken up so early. 6 He told Terry to get lost and hung up. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Focus structure and pronoun interpretation

1 Terry really goofs sometimes. 2 Yesterday was a beautiful day and he was excited about trying

his new sailboat.

3 He wanted Tony to join him on a sailing expedition. 4 He called him at 6 am. 5 Tony was sick and furious at being woken up so early. 6 He told Terry to get lost and hung up. 7 Of course, Terry hadn’t intended to upset Tony. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Modelling Focus in Centering Theory

Every utterance Un has a backwards looking center Cb, which connects Un with the preceding utterance Un−1. For discourse initial utterances Cb is undefined. Each utterance Un also has a partially ordered set of forward looking centers Cf , which form a potential link with the following utterance Un+1 The partial order of Cf is determined, among others, by the grammatical role of the referring expression, i.e., Subject ≺ Object ≺ Others (subject before object before

• thers)

The highest ranking element in the Cf of an utterance is the prefered center Cp. The Cb of an utterance Un is the highest ranking element in the Cf of Un−1, which is realised in Un

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John} Cf = {Mike, him=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John} Cf = {Mike, him=John} Cp={Mike}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John} Cf = {Mike, him=John} Cp={Mike} He phoned John at 5 o’clock in the morning last Friday.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John} Cf = {Mike, him=John} Cp={Mike} He phoned John at 5 o’clock in the morning last Friday. Cb={he=Mike}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John} Cf = {Mike, him=John} Cp={Mike} He phoned John at 5 o’clock in the morning last Friday. Cb={he=Mike} Cf = {he=Mike, John, Friday, 5 o’clock}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example

John has many problems with organising his holidays. Cb={undef} Cf = {John, problems, holidays} Cp={John} He cannot find anybody to take over his duties. Cb={he=John} Cf = {he=John, anybody, duties} Cp={he=John} Yesterday he phoned Mike to make a plan. Cb={he=John} Cf = {he=John, Mike, plan} Cp={he=John} Mike has annoyed him very much recently. Cb={him=John} Cf = {Mike, him=John} Cp={Mike} He phoned John at 5 o’clock in the morning last Friday. Cb={he=Mike} Cf = {he=Mike, John, Friday, 5 o’clock} Cp = {he=Mike}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions

different types of center transitions are possible, depending on whether whether the Cb continues or not the chosen center transitions determine the coherence of a text Cb(Un) = Cb(Un−1) Cb(Un) = Cb(Un−1)

• r undefined Cb(Un)

Cb(Un) = Cp(Un) Continue Smooth-Shift Cb(Un) = Cp(Un) Retain Rough-Shift Preferred order for transitions: Continue > Retain > Smooth − Shift > Rough − Shift

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions

different types of center transitions are possible, depending on whether whether the Cb continues or not the chosen center transitions determine the coherence of a text Cb(Un) = Cb(Un−1) Cb(Un) = Cb(Un−1)

• r undefined Cb(Un)

Cb(Un) = Cp(Un) Continue Smooth-Shift Cb(Un) = Cp(Un) Retain Rough-Shift Preferred order for transitions: Continue > Retain > Smooth − Shift > Rough − Shift

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions

different types of center transitions are possible, depending on whether whether the Cb continues or not the chosen center transitions determine the coherence of a text Cb(Un) = Cb(Un−1) Cb(Un) = Cb(Un−1)

• r undefined Cb(Un)

Cb(Un) = Cp(Un) Continue Smooth-Shift Cb(Un) = Cp(Un) Retain Rough-Shift Preferred order for transitions: Continue > Retain > Smooth − Shift > Rough − Shift

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue Mike has annoyed him very much recently.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue Mike has annoyed him very much recently. Cb={him=John}, Cf = {Mike, him=John}, Cp={Mike}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue Mike has annoyed him very much recently. Cb={him=John}, Cf = {Mike, him=John}, Cp={Mike} Transition: Retain

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue Mike has annoyed him very much recently. Cb={him=John}, Cf = {Mike, him=John}, Cp={Mike} Transition: Retain He phoned John at 5 o’clock in the morning last Friday.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue Mike has annoyed him very much recently. Cb={him=John}, Cf = {Mike, him=John}, Cp={Mike} Transition: Retain He phoned John at 5 o’clock in the morning last Friday. Cb={he=Mike}, Cf = {he=Mike, John, Friday, 5 o’clock, Cp={he=Mike}

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Center Transitions: Example

John has many problems with organising his holidays. Cb={undef}, Cf = {John, problems, holidays}, Cp={John} He cannot find anybody to take over his duties. Cb={he=John}, Cf = {he=John, anybody, duties}, Cp={he=John} Transition: Continue Yesterday he phoned Mike to make a plan. Cb={he=John}, Cf = {John, Mike, plan}, Cp={he=John} Transition: Continue Mike has annoyed him very much recently. Cb={him=John}, Cf = {Mike, him=John}, Cp={Mike} Transition: Retain He phoned John at 5 o’clock in the morning last Friday. Cb={he=Mike}, Cf = {he=Mike, John, Friday, 5 o’clock, Cp={he=Mike} Transition: Smooth-Shift

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Claims of Centering Theory

each Un has a unique Cb the Cf elements are partially ranked according to a number of factors (exactly which ones is not totally clear) centering constrains realisation possibilities (esp. choice of pronouns) there is a preference among sequences of center transitions (violations of these preferences typically results in incoherence) Cb(Un) is strictly local; it has to be chosen from Cf (Un−1) not from the Cf of an earlier utterance centering is controlled by a combination of discourse factors

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns

Rule 1 If any element of Cf (Un) is realised by a pronoun in Un+1, then the Cb(Un+1) must be realised by a pronoun also. (=If some element in an utterance is realised by a pronoun than the backward looking center of that utterance must also be realised as a pronoun.)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently.

[Cb={he=John}]

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently.

[Cb={he=John}]

3 He called up Mike yesterday. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently.

[Cb={he=John}]

3 He called up Mike yesterday.

[Cb={he=John}]

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently.

[Cb={he=John}]

3 He called up Mike yesterday.

[Cb={he=John}]

4 John wanted to meet him urgently. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently.

[Cb={he=John}]

3 He called up Mike yesterday.

[Cb={he=John}]

4 John wanted to meet him urgently.

[Cb={John} him=Mike]

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently.

[Cb={he=John}]

3 He called up Mike yesterday.

[Cb={he=John}]

4 John wanted to meet him urgently.

[Cb={John} him=Mike] ⇒ Discourse is perceived as incoherent because (4) violates Rule 1

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

Rule 1 applies independent of the grammatical position of Cb

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently. 3 He called up Mike yesterday. 4 He was annoyed by John’s call. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering and Choice of Pronouns: Example

Rule 1 applies independent of the grammatical position of Cb

1 I don’t know what’s the matter with John. 2 He has been acting quite odd recently. 3 He called up Mike yesterday. 4 He was annoyed by John’s call. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

A more complex Centering Example

Madagascar is an island nation in the Indian Ocean off the southeastern coast of Africa. The main island, also called Madagascar2, is the fourth-largest island in the world, and is home to 5% of the world’s plant and animal species. Madagascar split from Africa approximately 160 million years ago. Most archaeologists estimate that the human settlement of Madagascar happened between 200 and 500 A.D., when seafarers from southeast Asia arrived in outrigger sailing canoes. Bantu settlers probably crossed the Mozambique Channel to Madagascar at about the same time or shortly afterwards.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

A more complex Centering Example

Madagascar is an island nation in the Indian Ocean off the southeastern coast of Africa. Cb={} Cf ={Madagascar1, Indian Ocean, SE coast of Africa} The main island, also called Madagascar2, is the fourth-largest island in the world, and is home to 5% of the world’s plant and animal species. Madagascar split from Africa approximately 160 million years ago. Most archaeologists estimate that the human settlement of Madagascar happened between 200 and 500 A.D., when seafarers from southeast Asia arrived in outrigger sailing canoes. Bantu settlers probably crossed the Mozambique Channel to Madagascar at about the same time or shortly afterwards.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

A more complex Centering Example

Madagascar is an island nation in the Indian Ocean off the southeastern coast of Africa. Cb={} Cf ={Madagascar1, Indian Ocean, SE coast of Africa} The main island, also called Madagascar2, is the fourth-largest island in the world, and is home to 5% of the world’s plant and animal species. Cb={Madagascar2} Cf ={the main island=Madagascar2=the 4th largest island in the world ≈bridge Madagascar1, 5% of the world’s ...} continue Madagascar split from Africa approximately 160 million years ago. Most archaeologists estimate that the human settlement of Madagascar happened between 200 and 500 A.D., when seafarers from southeast Asia arrived in outrigger sailing canoes. Bantu settlers probably crossed the Mozambique Channel to Madagascar at about the same time or shortly afterwards.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

A more complex Centering Example

Madagascar is an island nation in the Indian Ocean off the southeastern coast of Africa. Cb={} Cf ={Madagascar1, Indian Ocean, SE coast of Africa} The main island, also called Madagascar2, is the fourth-largest island in the world, and is home to 5% of the world’s plant and animal species. Cb={Madagascar2} Cf ={the main island=Madagascar2=the 4th largest island in the world ≈bridge Madagascar1, 5% of the world’s ...} continue Madagascar split from Africa approximately 160 million years ago. Cb={Madagascar2} Cf ={Madagascar2, Africa} continue Most archaeologists estimate that the human settlement of Madagascar happened between 200 and 500 A.D., when seafarers from southeast Asia arrived in outrigger sailing canoes. Bantu settlers probably crossed the Mozambique Channel to Madagascar at about the same time or shortly afterwards.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

A more complex Centering Example

Madagascar is an island nation in the Indian Ocean off the southeastern coast of Africa. Cb={} Cf ={Madagascar1, Indian Ocean, SE coast of Africa} The main island, also called Madagascar2, is the fourth-largest island in the world, and is home to 5% of the world’s plant and animal species. Cb={Madagascar2} Cf ={the main island=Madagascar2=the 4th largest island in the world ≈bridge Madagascar1, 5% of the world’s ...} continue Madagascar split from Africa approximately 160 million years ago. Cb={Madagascar2} Cf ={Madagascar2, Africa} continue Most archaeologists estimate that the human settlement of Madagascar happened between 200 and 500 A.D., when seafarers from southeast Asia arrived in outrigger sailing canoes. Cb={Madagascar2} Cf ={most archaeologists, the human settlement of Madagascar, Madagascar2, seafarers, SE Asia, outrigger sailing canoes} retain Bantu settlers probably crossed the Mozambique Channel to Madagascar at about the same time or shortly afterwards.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

A more complex Centering Example

Madagascar is an island nation in the Indian Ocean off the southeastern coast of Africa. Cb={} Cf ={Madagascar1, Indian Ocean, SE coast of Africa} The main island, also called Madagascar2, is the fourth-largest island in the world, and is home to 5% of the world’s plant and animal species. Cb={Madagascar2} Cf ={the main island=Madagascar2=the 4th largest island in the world ≈bridge Madagascar1, 5% of the world’s ...} continue Madagascar split from Africa approximately 160 million years ago. Cb={Madagascar2} Cf ={Madagascar2, Africa} continue Most archaeologists estimate that the human settlement of Madagascar happened between 200 and 500 A.D., when seafarers from southeast Asia arrived in outrigger sailing canoes. Cb={Madagascar2} Cf ={most archaeologists, the human settlement of Madagascar, Madagascar2, seafarers, SE Asia, outrigger sailing canoes} retain Bantu settlers probably crossed the Mozambique Channel to Madagascar at about the same time or shortly afterwards. Cb={Madagascar2} Cf ={Bantu settlers, the Mozambique Channel, Madagascar} retain

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering Theory Revisited

Centering Theory in its original formulation was a linguistic theory rather than a computational one. Many aspects were left unspecified or not formalised. Researchers taking up the theory proposed different formalisations.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering Theory: Open Questions

What is an “utterance” (sentence or clause)? Exactly how are the Cf s ranked? What exactly does it mean that an element is “realised” in an utterance? Are empty Cbs allowed in non-initial sentences? Are the additional transition types? ⇒ much subsequent research into these parameters of Centering Theory (see e.g., Poesio et al. 2004)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example: Problems with “Realisation”

Bridging expressions

1 Madagascar is an island nation in the Indian Ocean. 2 The main island is the fourth largest island in the world. Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example: Problems with “Realisation”

Bridging expressions

1 Madagascar is an island nation in the Indian Ocean. 2 The main island is the fourth largest island in the world.

⇒ “Madagascar” is realised indirectly in (2)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Example: Problems with “Realisation”

Bridging expressions

1 Madagascar is an island nation in the Indian Ocean. 2 The main island is the fourth largest island in the world.

⇒ “Madagascar” is realised indirectly in (2) Similar problems with ellipses etc.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering Theory Revisited

Poesio et al. (2004) conducted an extensive corpus study to determine which instantiations of Centering Theory fit the data best. Main findings: parameter settings matter

for vanilla instantiation some of Centering’s main claims are frequently violated (e.g., the claim that all non-initial utterances have a unique Cb) it is possible to find alternative instantiation which minimise rule variations

crucial parameters are: what counts as an utterance?, what entities are included in the Cf?, how is realisation defined?

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering as a theory of discourse coherence

Poesio et al. (2004) and Karamanis (2003): Many texts are not maximally coherent wrt Centering Theory but in most of these cases it is not possible to make the texts more coherent wrt Centering.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Centering as a theory of discourse coherence

Poesio et al. (2004) and Karamanis (2003): Many texts are not maximally coherent wrt Centering Theory but in most of these cases it is not possible to make the texts more coherent wrt Centering. ⇒ Centering Theory only partially captures coherence, rhetorical relations may capture another part

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse Coherence Beyond Centering

Example (u1) This leaflet is a summary of the important information about Product A. (u2) If you have any questions or are not sure about anything to do with your treatment, (u3) ask your doctor or pharmacist.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Discourse Coherence Beyond Centering

Example (u1) On the drawer above the door, gilt-bronze military trophies flank a medallion portrait of Louis XIV. (u2) In the Dutch Wars of 1672-1678, France fought simultaneously against the Dutch, Spanish, and Imperial armies, defeating them all. (u3) This cabinet celebrates the Treaty of Nijmegen, which concluded the war.

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse

Summary

Lexical Chains model lexical cohesion correspond to sub-topics in a text their computation requires a measure of semantic relatedness and the choice of a chain building algorithm are useful for a number of applications Centering Theory models focus structure can explain coherence (related to inference load) and pronoun realisation the best parametrisation is still an open research area (partly language dependent) also several applications (any ideas?)

Caroline Sporleder csporled@coli.uni-sb.de Computational Models of Discourse