Introduction to Natural Language Processing a course taught as - - PowerPoint PPT Presentation

▶
introduction to natural language processing
SMART_READER_LITE
LIVE PREVIEW

Introduction to Natural Language Processing a course taught as - - PowerPoint PPT Presentation

Dec 09, 2023 22 likes •1.1k views

Introduction to Natural Language Processing a course taught as B4M36NLP at Open Informatics by members of the Institute of Formal and Applied Linguistics Today: Week 6, lab Todays topic: Universal Dependencies Todays teacher: Daniel

slide-1
SLIDE 1

Introduction to Natural Language Processing

a course taught as B4M36NLP at Open Informatics by members of the Institute of Formal and Applied Linguistics Today: Week 6, lab Today’s topic: Universal Dependencies Today’s teacher: Daniel Zeman

E-mail: zeman@ufal.mff.cuni.cz WWW: http://ufal.mff.cuni.cz/daniel-zeman

Daniel Zeman (´ UFAL MFF UK) Universal Dependencies Week 6, lab 1 / 1

slide-2
SLIDE 2

29.9.2016, Ljubljana 2

Dependency Treebanks

slide-3
SLIDE 3

29.9.2016, Ljubljana 3

Dependency Treebanks

slide-4
SLIDE 4

29.9.2016, Ljubljana 4

Why?

  • Linguistic research

– Corpus query

  • Training tools (parsers) for NLP

– Downstream applications

slide-5
SLIDE 5

29.9.2016, Ljubljana 5

slide-6
SLIDE 6

29.9.2016, Ljubljana 6

slide-7
SLIDE 7

29.9.2016, Ljubljana 7

slide-8
SLIDE 8

29.9.2016, Ljubljana 8

slide-9
SLIDE 9

29.9.2016, Ljubljana 9

slide-10
SLIDE 10

29.9.2016, Ljubljana 10

Universal Dependencies

http://universaldependencies.org/

slide-11
SLIDE 11

29.9.2016, Ljubljana 11

Universal Dependencies

Stanford Dependencies

http://universaldependencies.org/

slide-12
SLIDE 12

29.9.2016, Ljubljana 12

Universal Dependencies

Stanford Dependencies CLEAR

http://universaldependencies.org/

slide-13
SLIDE 13

29.9.2016, Ljubljana 13

Universal Dependencies

Stanford Dependencies CLEAR Google UD

http://universaldependencies.org/

slide-14
SLIDE 14

29.9.2016, Ljubljana 14

Universal Dependencies

Stanford Dependencies CLEAR Google UD Stanford UD

http://universaldependencies.org/

slide-15
SLIDE 15

29.9.2016, Ljubljana 15

Universal Dependencies

Stanford Dependencies CLEAR Google UD Stanford UD HamleDT

http://universaldependencies.org/

slide-16
SLIDE 16

29.9.2016, Ljubljana 16

Universal Dependencies

Stanford Dependencies CLEAR Google UD Stanford UD HamleDT Interset

http://universaldependencies.org/

slide-17
SLIDE 17

29.9.2016, Ljubljana 17

Universal Dependencies

Stanford Dependencies CLEAR Google UD Stanford UD HamleDT Interset Google universal tags

http://universaldependencies.org/

slide-18
SLIDE 18

29.9.2016, Ljubljana 18

Universal Dependencies

http://universaldependencies.org/

Universal Dependencies

slide-19
SLIDE 19

29.9.2016, Ljubljana 19

Universal Dependencies

  • Milestones:

–

2014-04: EACL Göteborg, kick-off meeting

–

2014-10: UD guidelines version 1

–

2015-01: released 10 treebanks of 10 languages (UD 1.0)

–

2015-05: released 19 treebanks of 18 languages (UD 1.1)

–

2015-11: released 37 treebanks of 33 languages (UD 1.2)

–

2016-05: released 54 treebanks of 40 languages (UD 1.3)

–

2016-11: UD release 1.4, ~7 new languages

–

2016 fall: UD guidelines version 2

http://universaldependencies.org/

slide-20
SLIDE 20

29.9.2016, Ljubljana 20

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
slide-21
SLIDE 21

29.9.2016, Ljubljana 21

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
  • Support multilingual research and development in NLP
slide-22
SLIDE 22

29.9.2016, Ljubljana 22

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
  • Support multilingual research and development in NLP
  • Based on common usage and existing de facto

standards

slide-23
SLIDE 23

29.9.2016, Ljubljana 23

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
  • Support multilingual research and development in NLP
  • Based on common usage and existing de facto standards
  • Caveats:

– Not a new linguistic theory –

but linguistically informed and relevant Not an ideal parsing representation – but useful for comparative evaluation Not the ultimate annotation scheme – but a lightweight lingua franca

slide-24
SLIDE 24

29.9.2016, Ljubljana 24

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
  • Support multilingual research and development in NLP
  • Based on common usage and existing de facto standards
  • Caveats:

– Not a new linguistic theory –

but linguistically informed and relevant

– Not an ideal parsing representation –

but useful for comparative evaluation Not the ultimate annotation scheme – but a lightweight lingua franca

slide-25
SLIDE 25

29.9.2016, Ljubljana 25

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
  • Support multilingual research and development in NLP
  • Based on common usage and existing de facto standards
  • Caveats:

– Not a new linguistic theory –

but linguistically informed and relevant

– Not an ideal parsing representation –

but useful for comparative evaluation

– Not the ultimate annotation scheme –

but a lightweight lingua franca

slide-26
SLIDE 26

29.9.2016, Ljubljana 26

Goals and Requirements

  • Cross-linguistically consistent grammatical annotation
  • Support multilingual research and development in NLP
  • Based on common usage and existing de facto standards
  • Caveats:

– Not a new linguistic theory –

but linguistically informed and relevant

– Not an ideal parsing representation –

but useful for comparative evaluation

– Not the ultimate annotation scheme –

but a lightweight lingua franca Not “Universal” in the strictly typological sense!

slide-27
SLIDE 27

29.9.2016, Ljubljana 27

Design Principles

  • Dependency

– Widely used in practical NLP systems – Available in treebanks for many languages

slide-28
SLIDE 28

29.9.2016, Ljubljana 28

Design Principles

  • Dependency

– Widely used in practical NLP systems – Available in treebanks for many languages

  • Lexicalism

– Basic annotation units are words – syntactic words – Words have morphological properties – Words enter into syntactic relations

slide-29
SLIDE 29

29.9.2016, Ljubljana 29

Design Principles

  • Dependency

– Widely used in practical NLP systems – Available in treebanks for many languages

  • Lexicalism

– Basic annotation units are words – syntactic words – Words have morphological properties – Words enter into syntactic relations

  • Recoverability

– Transparent mapping from input text to word segmentation

slide-30
SLIDE 30

29.9.2016, Ljubljana 30

Golden Rules

  • Maximize parallelism

– Don’t annotate the same thing in different ways – Don’t make different things look the same

slide-31
SLIDE 31

29.9.2016, Ljubljana 31

Golden Rules

  • Maximize parallelism

– Don’t annotate the same thing in different ways – Don’t make different things look the same

  • But don’t overdo it

– Don’t annotate things that are not there – Balance: is it still the same thing? – Allow language-specific extensions

slide-32
SLIDE 32

29.9.2016, Ljubljana 32

Morphology

Některé dívky si nicméně pochvalovaly zmrzlinu . některý dívka se nicméně pochvalovat zmrzlina . DET NOUN PRON CONJ VERB NOUN PUNCT

PronType=Ind Gender=Fem Number=Plur Case=Nom Gender=Fem Number=Plur Case=Nom PronType=Prs Reflex=Yes Case=Dat VerbForm=Part Tense=Past Voice=Act Aspect=Imp Gender=Fem Number=Plur Gender=Fem Number=Sing Case=Acc

slide-33
SLIDE 33

29.9.2016, Ljubljana 33

Morphology

Některé dívky si nicméně pochvalovaly zmrzlinu . některý dívka se nicméně pochvalovat zmrzlina . DET NOUN PRON CONJ VERB NOUN PUNCT

PronType=Ind Gender=Fem Number=Plur Case=Nom Gender=Fem Number=Plur Case=Nom PronType=Prs Reflex=Yes Case=Dat VerbForm=Part Tense=Past Voice=Act Aspect=Imp Gender=Fem Number=Plur Gender=Fem Number=Sing Case=Acc

  • Lemma representing the semantic content of the word
slide-34
SLIDE 34

29.9.2016, Ljubljana 34

Morphology

Některé dívky si nicméně pochvalovaly zmrzlinu . některý dívka se nicméně pochvalovat zmrzlina . DET NOUN PRON CONJ VERB NOUN PUNCT

PronType=Ind Gender=Fem Number=Plur Case=Nom Gender=Fem Number=Plur Case=Nom PronType=Prs Reflex=Yes Case=Dat VerbForm=Part Tense=Past Voice=Act Aspect=Imp Gender=Fem Number=Plur Gender=Fem Number=Sing Case=Acc

  • Lemma representing the semantic content of the word
  • Part-of-speech tag representing the abstract lexical category

associated with the word

slide-35
SLIDE 35

29.9.2016, Ljubljana 35

Morphology

Některé dívky si nicméně pochvalovaly zmrzlinu . některý dívka se nicméně pochvalovat zmrzlina . DET NOUN PRON CONJ VERB NOUN PUNCT

PronType=Ind Gender=Fem Number=Plur Case=Nom Gender=Fem Number=Plur Case=Nom PronType=Prs Reflex=Yes Case=Dat VerbForm=Part Tense=Past Voice=Act Aspect=Imp Gender=Fem Number=Plur Gender=Fem Number=Sing Case=Acc

  • Lemma representing the semantic content of the word
  • Part-of-speech tag representing the abstract lexical category associated

with the word

  • Features representing lexical and grammatical properties associated with

the lemma or the particular word form

slide-36
SLIDE 36

29.9.2016, Ljubljana 36

Part-of-Speech Tags

Open Closed Other ADJ ADP PUNCT ADV AUX SYM INTJ CONJ X NOUN DET PROPN NUM VERB PART PRON SCONJ

  • Taxonomy of 17 universal part-of-speech tags, based on the

Google Universal Tagset (Petrov et al., 2012)

  • All languages use the same inventory, but not all tags have to

be used by all languages

slide-37
SLIDE 37

29.9.2016, Ljubljana 37

Features

Lexical Inflectional / Nominal Inflectional / Verbal PronType Gender VerbForm NumType Animacy Mood Poss Number Tense Reflex Case Aspect Definite Voice Degree Person Negative

  • Standardized inventory of morphological features, based on

Interset (Zeman, 2008)

  • Languages select relevant features and can add language-

specific features or values with documentation

slide-38
SLIDE 38

29.9.2016, Ljubljana 38

Syntax

slide-39
SLIDE 39

29.9.2016, Ljubljana 39

Syntax

  • Content words are related by dependency relations
slide-40
SLIDE 40

29.9.2016, Ljubljana 40

Syntax

  • Content words are related by dependency relations
  • Function words attach to closest content word
slide-41
SLIDE 41

29.9.2016, Ljubljana 41

Syntax

  • Content words are related by dependency relations
  • Function words attach to closest content word
  • Punctuation attach to head of phrase or clause
slide-42
SLIDE 42

29.9.2016, Ljubljana 42

Syntax

  • Content words are related by dependency relations
  • Function words attach to closest content word
  • Punctuation attach to head of phrase or clause

Not “dependency” in the strictly syntactic sense!

slide-43
SLIDE 43

29.9.2016, Ljubljana 43

slide-44
SLIDE 44

29.9.2016, Ljubljana 44

slide-45
SLIDE 45

29.9.2016, Ljubljana 45

slide-46
SLIDE 46

29.9.2016, Ljubljana 47

Dependency Relations

  • Taxonomy of 40 universal grammatical relations,

broadly attested in language typology (de Marneffe et al., 2014)

– Language-specific subtypes may be added

slide-47
SLIDE 47

29.9.2016, Ljubljana 48

Dependency Relations

  • Taxonomy of 40 universal grammatical relations,

broadly attested in language typology (de Marneffe et al., 2014)

– Language-specific subtypes may be added

  • Organizing principles

– Three types of structures: nominals, clauses, modifiers – Core arguments vs. other dependents (not arguments

  • vs. adjuncts)
slide-48
SLIDE 48

29.9.2016, Ljubljana 49

Dependents of Clausal Predicates

Nominal Clausal Other Core nsubj nsubjpass dobj iobj csubj csubjpass ccomp xcomp Non-Core nmod vocative discourse expl advcl advmod neg aux auxpass cop mark punct

slide-49
SLIDE 49

29.9.2016, Ljubljana 50

slide-50
SLIDE 50

29.9.2016, Ljubljana 51

Dependents of Nominals

Nominal Clausal Other nmod appos nummod acl amod det neg case

slide-51
SLIDE 51

29.9.2016, Ljubljana 52

“Stanford-style” Coordination

  • Coordinate structures are headed by the first conjunct

– Subsequent conjuncts depend on it via the conj relation – Conjunctions depend on it via the cc relation – Punctuation marks depend on it via the punct relation

slide-52
SLIDE 52

29.9.2016, Ljubljana 53

Multiword Expressions

Relation Examples mwe in spite of, as well as, ad hoc name Roger Bacon, New York compound phone book, four thousand, dress up goeswith notwith standing, with out

  • UD annotation does not permit “words with spaces”

– Multiword expressions are analyzed using special relations – The mwe, name and goeswith relations are always head-initial – The compound relation reflects the internal structure

slide-53
SLIDE 53

29.9.2016, Ljubljana 54

Other Relations

Relation Explanation parataxis Loosely linked clauses of same rank list Lists without syntactic structure remnant Orphans in ellipsis linked to parallel elements reparandum Disfluency linked to (speech) repair foreign Elements within opaque stretches of code switching dep Unspecified dependency root Syntactically independent element of clause/phrase

slide-54
SLIDE 54

29.9.2016, Ljubljana 55

Language-Specific Relations

  • Language-specific relations are subtypes of universal

relations added to capture important phenomena

  • Subtyping permits us to “back off” to universal relations

Relation Explanation acl:relcl Relative clause compound:prt Verb particle (dress up) nmod:poss Genitive nominal (Mary ’s book) nmod:agent Agent in passive (saved by the bell) cc:preconj Preconjunction (both … and) det:predet Predeterminer (all those …)

slide-55
SLIDE 55

29.9.2016, Ljubljana 56

Word Segmentation

  • Must be reproducible on new data
  • Surface tokens vs. syntactic words
  • Chinese, Vietnamese etc.: no clues, non-trivial algorithm
  • Arabic, Tamil etc.: part of morphological analysis
  • Spanish, German etc.: rather limited cases of contractions
  • Others: only punctuation (low-level tokenization)
slide-56
SLIDE 56

29.9.2016, Ljubljana 57

Word Segmentation

  • Fusions

– al = a + el – naň = na + něj

  • Clitics

– vámonos = vamos + nos – изменяться = изменять + ся – potrafilibyśmy

= potrafili + by + jesteśmy

slide-57
SLIDE 57

29.9.2016, Ljubljana 58

Where Are We Now?

slide-58
SLIDE 58

29.9.2016, Ljubljana 59

Where Are We Now?

  • Two years of UD version 1
  • 4 treebank releases (every 6 months)
  • 54 (61) treebanks
  • 40 (47) languages (over 50% world’s population)
  • Over 11M tokens; treebanks range from 1K to 1.5M
  • Over 120 contributors

– language group consistency SIGs – version 2 guidelines coming soon

slide-59
SLIDE 59

29.9.2016, Ljubljana 60

47 Languages and Growing

slide-60
SLIDE 60

29.9.2016, Ljubljana 61

Where Are We Going?

  • UD guidelines version 2 coming soon
  • Consistency checking
slide-61
SLIDE 61

29.9.2016, Ljubljana 62

Common vocabulary is great …

… because we finally understand each other …

slide-62
SLIDE 62

29.9.2016, Ljubljana 63

… almost

Childs of you be vary acute!

From RenetteLouwLouw (own work) [CC BY-SA 4.0 (http://creativecommons.org/licenses/by-sa/4.0)], through Wikimedia Commons

slide-63
SLIDE 63

29.9.2016, Ljubljana 64

Consistency Checking

  • Automatic tests catch only a fraction
  • Focus groups on

– Romance, Germanic, Slavic, Uralic, Turkic languages

slide-64
SLIDE 64

29.9.2016, Ljubljana 65

Existing Slavic Treebanks

?

slide-65
SLIDE 65

29.9.2016, Ljubljana 66

Issues of Slavic Languages in UD

  • Pronouns vs. determiners, numerals and quantifiers
  • Attachment of cardinal numbers
  • Verbs, participles, adjectives
  • Core arguments
  • Reflexive pronouns (clitics)
  • Auxiliary verbs and modal verbs
  • Comparative constructions
slide-66
SLIDE 66

29.9.2016, Ljubljana 67

Pronouns and Determiners

  • English + Romance languages: DET = article or pronominal

adjective (this, which, every)

slide-67
SLIDE 67

29.9.2016, Ljubljana 68

Pronouns and Determiners

  • English + Romance languages: DET = article or pronominal

adjective (this, which, every)

  • We don’t have this category! (Traditionally → PRON.)
slide-68
SLIDE 68

29.9.2016, Ljubljana 69

Pronouns and Determiners

  • English + Romance languages: DET = article or pronominal

adjective (this, which, every)

  • We don’t have this category! (Traditionally → PRON.)
  • Some authors do recognize

determiners in Slavic!

slide-69
SLIDE 69

29.9.2016, Ljubljana 70

Pronouns and Determiners

  • English + Romance languages: DET = article or pronominal

adjective (this, which, every)

  • We don’t have this category! (Traditionally → PRON.)
  • We have the words (except for articles).
slide-70
SLIDE 70

29.9.2016, Ljubljana 71

Pronouns and Determiners

  • English + Romance languages: DET = article or pronominal

adjective (this, which, every)

  • We don’t have this category! (Traditionally → PRON.)
  • We have the words (except for articles).
  • Currently functional borderline (but ellipsis?)

This.DET car is expensive. This.PRON is expensive.

  • Less strict in UD v2.
slide-71
SLIDE 71

29.9.2016, Ljubljana 72

Pronouns Only

  • Personal pronouns (including reflexives, but not possessives)
  • Interrogative who, what
  • Indefinite and negative derivatives
  • Relative [cs] jenž

– cs: já, ty, on, my, vy, oni, se, kdo, co, někdo, něco, nikdo, nic – sk: ja, ty, on, my, vy, oni, sa, kto, čo, niekto, niečo, nikto, nič – pl: ja, ty, on, my, wy, oni, się, kto, co, ktoś, coś, nikt, nic – ru: я, ты, он, мы, вы, они, ся, кто, что, кто-нибудь, что-нибудь, никто, ничто – sl: jaz, ti, on, mi, vi, oni, se, kdo, kaj, nekdo, nekaj, nihče, nič – hr: ja, ti, on, mi, vi, oni, se, tko, što, neki, nešto, nitko, ništa – bg: аз, ти, ние, вие, се, кой, кое, някой, нещо, никой, нищо – cu: азъ, тꙑ, мꙑ, вꙑ, и, сѧ, къто, чьто

slide-72
SLIDE 72

29.9.2016, Ljubljana 73

Possessives: Determiners

  • If they occur without a noun … ellipsis

Můj otec je starší. Tvůj má ale více zkušeností. My father is older. But yours is more experienced.

  • sl: moj, tvoj, njegov, njen, najin, vajin, njun, naš, vaš, njihov, svoj
  • bg: мой, твой, негов, неин, наш, ваш, техен, свой
  • cs: můj, tvůj, jeho, její, náš, váš, jejich, svůj
  • sk: môj, tvoj, jeho, jej, náš, váš, ich, svoj
  • cu: мои, твои, нашь, вашь, свои / его, еѩ, ею, ихъ
slide-73
SLIDE 73

29.9.2016, Ljubljana 74

Both Possible?

  • Demonstratives

– cs: ten, to, tento, tenhle, tamten, … – sl: ta, to, tisti, oni, takšen, …

  • Adjectival interrogatives/relatives, indefinites, negatives

– jaký, který, čí, nějaký, některý, něčí, každý, žádný – všechen, všichni, všechno

  • Relative pronouns cannot be explained by ellipsis!

– Muž, kterého *muže jsem vám představil. – The man, which *man I introduced to you.

slide-74
SLIDE 74

29.9.2016, Ljubljana 81

Issues of Slavic Languages in UD

  • Pronouns vs. determiners, numerals and quantifiers
  • Attachment of cardinal numbers
  • Verbs, participles, adjectives
  • Core arguments
  • Reflexive pronouns (clitics)
  • Auxiliary verbs and modal verbs
  • Comparative constructions
slide-75
SLIDE 75

29.9.2016, Ljubljana 82

Quantified Noun Phrase

slide-76
SLIDE 76

29.9.2016, Ljubljana 83

Quantified Noun Phrase

slide-77
SLIDE 77

29.9.2016, Ljubljana 84

Quantified Noun Phrase

Genitive!

slide-78
SLIDE 78

29.9.2016, Ljubljana 85

Quantified Noun Phrase

slide-79
SLIDE 79

29.9.2016, Ljubljana 86

Quantified Noun Phrase

slide-80
SLIDE 80

29.9.2016, Ljubljana 87

Pronominal Quantifiers

slide-81
SLIDE 81

29.9.2016, Ljubljana 93

Language-Specific Labels

slide-82
SLIDE 82

29.9.2016, Ljubljana 94

Issues of Slavic Languages in UD

  • Pronouns vs. determiners, numerals and quantifiers
  • Attachment of cardinal numbers
  • Verbs, participles, adjectives
  • Core arguments
  • Reflexive pronouns (clitics)
  • Auxiliary verbs and modal verbs
  • Comparative constructions
slide-83
SLIDE 83

29.9.2016, Ljubljana 95

Verb Forms

  • Conflicting terminologies in traditional

grammars

  • Participle … verb or adjective?
  • Converb … verb or adverb?
  • Tags and features apply to individual words!
slide-84
SLIDE 84

29.9.2016, Ljubljana 96

Verb Forms

  • POS tags and features apply to individual words!
  • A ko so se leta 1942 vračali, …

– past tense

  • … da ne bi v Atene prišli …

– conditional mood

  • … v prihodnje ne bodo vozili zgolj les …

– future tense

slide-85
SLIDE 85

29.9.2016, Ljubljana 97

Verb Forms

  • POS tags and features apply to individual words!
  • A ko so se leta 1942 vračali, …

– past tense

  • … da ne bi v Atene prišli …

– conditional mood

  • … v prihodnje ne bodo vozili zgolj les …

– future tense

Present Conditional Future

slide-86
SLIDE 86

29.9.2016, Ljubljana 98

Verb Forms

  • POS tags and features apply to individual words!
  • A ko so se leta 1942 vračali, …

– past tense

  • … da ne bi v Atene prišli …

– conditional mood

  • … v prihodnje ne bodo vozili zgolj les …

– future tense

Present Conditional Future Participle Participle Participle Past???

slide-87
SLIDE 87

29.9.2016, Ljubljana 99

Verb Forms

  • vračali, prišli, vozili
  • [cs] “active participle” / “past tense”
  • [ru] “past tense” / “finite!”

– Active participle is something else: нарушивший

  • [bg] “participle + past (aorist) / imperfect” (two subtypes)
  • [cu] “participle + resultative aspect” (lang-spec)
  • “l-participle”

– But that would be a language-specific verb form.

slide-88
SLIDE 88

29.9.2016, Ljubljana 100

Issues of Slavic Languages in UD

  • Pronouns vs. determiners, numerals and quantifiers
  • Attachment of cardinal numbers
  • Verbs, participles, adjectives
  • Core arguments
  • Reflexive pronouns (clitics)
  • Auxiliary verbs and modal verbs
  • Comparative constructions
slide-89
SLIDE 89

29.9.2016, Ljubljana 101

Core Arguments

  • Easier cross-linguistically than argument-

adjunct?

  • Subject of intransitive verb
  • Agent of transitive verb
  • Patient (direct object) of transitive verb
  • Indirect object? Dative only?
slide-90
SLIDE 90

29.9.2016, Ljubljana 102

Core vs. Oblique Dependents

  • Core arguments: what exactly is it?
  • English:

– He gave John the book. (iobj) – He gave the book to John. (nmod)

  • Spanish:

– Dio el libro a John. (iobj)

  • Czech:

– Every Obj is translated to dobj, regardless the case and the

presence of preposition

slide-91
SLIDE 91

29.9.2016, Ljubljana 103

dobj / iobj

  • Not as easy as accusative vs. dative.
  • Default: dobj
  • Heuristics for iobj

– Cením si vaší pomoci. (Gen)

I appreciate your help.

– Čelíme velkým problémům. (Dat)

We are facing big problems.

– Nedisponuje takovým rozpočtem. (Ins)

He does not have such budget.

– Učí mou dceru fyziku. (2 × Acc)

He teaches my daughter physics.

slide-92
SLIDE 92

29.9.2016, Ljubljana 104

All Slavic Treebanks Have Non-Accusative “Direct” Objects

  • podrobit se testu; odpovídají smlouvě; jednat s někým
  • mówi o niej; używa wielkich słów
  • от которых зависит; относится к программам
  • potrebuje informacij; slediti evropskim smernicam;

ukvarjal se bom orožjem

  • odriče se imuniteta; priključiti se naporima
  • се характеризира с развитие; моля за внимание
slide-93
SLIDE 93

29.9.2016, Ljubljana 105

Reflexive Pronouns

  • Direct or indirect object (dobj, iobj):

Řízl se do prstu / Řízl ho do prstu.

– Including reciprocal usage:

Políbili se. / They kissed each other.

  • Inherently reflexive verbs: smát se, bát se / laugh, fear

– expl:pv (pronominal verb; previously compound)

  • Reflexive passive:

To se snadněji řekne než udělá. / That is easier said than done.

– expl:pass (previously auxpass:reflex)

  • Impersonal construction (~ passive?):

Zde se mluví německy. / German is spoken here.

– expl:impers

slide-94
SLIDE 94

29.9.2016, Ljubljana 106

Issues of Slavic Languages in UD

  • Pronouns vs. determiners, numerals and quantifiers
  • Attachment of cardinal numbers
  • Verbs, participles, adjectives
  • Core arguments
  • Reflexive pronouns (clitics)
  • Auxiliary verbs and modal verbs
  • Comparative constructions
slide-95
SLIDE 95

29.9.2016, Ljubljana 107

Modal Auxiliary in English

slide-96
SLIDE 96

29.9.2016, Ljubljana 108

Modal Verb in Czech

slide-97
SLIDE 97

29.9.2016, Ljubljana 109

Modal Adverb in Russian

slide-98
SLIDE 98

29.9.2016, Ljubljana 110

Modal / Control Verb in English

slide-99
SLIDE 99

29.9.2016, Ljubljana 111

Issues of Slavic Languages in UD

  • Pronouns vs. determiners, numerals and quantifiers
  • Attachment of cardinal numbers
  • Verbs, participles, adjectives
  • Core arguments
  • Reflexive pronouns (clitics)
  • Auxiliary verbs and modal verbs
  • Comparative constructions
slide-100
SLIDE 100

29.9.2016, Ljubljana 112

Comparative Constructions

slide-101
SLIDE 101

29.9.2016, Ljubljana 113

Comparative Constructions

slide-102
SLIDE 102

29.9.2016, Ljubljana 114

Wrapping Up

slide-103
SLIDE 103

29.9.2016, Ljubljana 115

Wrapping Up

  • UD has had a great start

Still a long way to go. Consistency matters! Get involved. It’s fun!

slide-104
SLIDE 104

29.9.2016, Ljubljana 116

Wrapping Up

  • UD has had a great start
  • Still a long way to go.

Consistency matters!

slide-105
SLIDE 105

29.9.2016, Ljubljana 117

Wrapping Up

  • UD has had a great start
  • Still a long way to go.

Consistency matters!

  • Get involved. It’s fun!
slide-106
SLIDE 106

29.9.2016, Ljubljana 118

Thank you! Questions? Děkuji! Otázky? Ďakujem! Otázky? Dziękuję! Pytania? Hvala! Pitanja? Hvala! Vprašanja? Благодаря! Въпроси? Спасибо! Вопросы? Благодарѭ! Въпроси?

slide-107
SLIDE 107

29.9.2016, Ljubljana 119