Semantic Analysis of Sentences: The Estonian Experience Haldur im - - PowerPoint PPT Presentation

▶

Jan 15, 2024 151 likes •624 views

Motivation Steps to Go Frames and Semantic Roles Summary Semantic Analysis of Sentences: The Estonian Experience Haldur im Heili Orav Neeme Kahusk Piia Taremaa University of Tartu Institute of Computer Science Liivi 2 308, Tartu,

SLIDE 1

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Semantic Analysis of Sentences: The Estonian Experience

Haldur Õim Heili Orav Neeme Kahusk Piia Taremaa

University of Tartu Institute of Computer Science Liivi 2 – 308, Tartu, Estonia

HLT 2010

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 2

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Outline

1

Motivation

2

Steps to Go

3

Frames and Semantic Roles

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 3

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Real language understanding in a limited domain

Real understanding of texts Semantic representation of what reader knows after reading the text Question answering Towards an intelligent device acting in real room

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 4

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Real language understanding in a limited domain

Real understanding of texts Semantic representation of what reader knows after reading the text Question answering Towards an intelligent device acting in real room

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 5

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Real language understanding in a limited domain

Real understanding of texts Semantic representation of what reader knows after reading the text Question answering Towards an intelligent device acting in real room

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 6

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Real language understanding in a limited domain

Real understanding of texts Semantic representation of what reader knows after reading the text Question answering Towards an intelligent device acting in real room

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 7

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

plain text morphological analysis and disambiguation syntactic analysis and disambiguation word sense disambiguation frame semantics (and disambiguation) inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 8

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

plain text morphological analysis and disambiguation syntactic analysis and disambiguation word sense disambiguation frame semantics (and disambiguation) inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 9

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

plain text morphological analysis and disambiguation syntactic analysis and disambiguation word sense disambiguation frame semantics (and disambiguation) inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 10

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

plain text morphological analysis and disambiguation syntactic analysis and disambiguation word sense disambiguation frame semantics (and disambiguation) inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 11

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

plain text morphological analysis and disambiguation syntactic analysis and disambiguation word sense disambiguation frame semantics (and disambiguation) inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 12

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

plain text morphological analysis and disambiguation syntactic analysis and disambiguation word sense disambiguation frame semantics (and disambiguation) inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 13

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

Mary went from Tartu to Riga Where Mary was? Mary was in Tartu Where Mary is? Mary is in Riga

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 14

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

Mary went from Tartu to Riga Where Mary was? Mary was in Tartu Where Mary is? Mary is in Riga

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 15

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

Mary went from Tartu to Riga Where Mary was? Mary was in Tartu Where Mary is? Mary is in Riga

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 16

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

Mary went from Tartu to Riga Where Mary was? Mary was in Tartu Where Mary is? Mary is in Riga

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 17

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Main problems

inventory of semantic roles moving from syntactic tree to a semantic frame inferences world knowledge

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 18

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Main problems

inventory of semantic roles moving from syntactic tree to a semantic frame inferences world knowledge

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 19

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Main problems

inventory of semantic roles moving from syntactic tree to a semantic frame inferences world knowledge

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 20

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Main problems

inventory of semantic roles moving from syntactic tree to a semantic frame inferences world knowledge

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 21

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Frames and Semantic Roles

“Estonian” frames: 4 basic motion frames

agentive (self-)motion non-agentive (self-)motion agentive (causing) motion non-agentive (causing) motion

Framenet frames: many motion frames — e.g. self_motion, cause_motion, using_vechile, mass_motion . . . (we are currently using 17)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 22

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Frames and Semantic Roles

“Estonian” frames: 4 basic motion frames

agentive (self-)motion non-agentive (self-)motion agentive (causing) motion non-agentive (causing) motion

Framenet frames: many motion frames — e.g. self_motion, cause_motion, using_vechile, mass_motion . . . (we are currently using 17)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 23

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Frames and Semantic Roles

“Estonian” frames: 4 basic motion frames

agentive (self-)motion non-agentive (self-)motion agentive (causing) motion non-agentive (causing) motion

Framenet frames: many motion frames — e.g. self_motion, cause_motion, using_vechile, mass_motion . . . (we are currently using 17)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 24

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Frames and Semantic Roles

“Estonian” frames: 4 basic motion frames

agentive (self-)motion non-agentive (self-)motion agentive (causing) motion non-agentive (causing) motion

Framenet frames: many motion frames — e.g. self_motion, cause_motion, using_vechile, mass_motion . . . (we are currently using 17)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 25

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Frames and Semantic Roles

“Estonian” frames: 4 basic motion frames

agentive (self-)motion non-agentive (self-)motion agentive (causing) motion non-agentive (causing) motion

Framenet frames: many motion frames — e.g. self_motion, cause_motion, using_vechile, mass_motion . . . (we are currently using 17)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 26

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Frames and Semantic Roles

“Estonian” frames: 4 basic motion frames

agentive (self-)motion non-agentive (self-)motion agentive (causing) motion non-agentive (causing) motion

Framenet frames: many motion frames — e.g. self_motion, cause_motion, using_vechile, mass_motion . . . (we are currently using 17)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 27

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

AGENTIVE SELF-MOTION HYPERONYM: MOTION ROLE STRUCTURE Participant Roles AGENT (participant who controls his/her activity, the instigator of the event)

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 28

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

FRAME: ASETSEMA1 ’be located’ Object: = Agent Loc = Locfrom Time = Timefrom FRAME: ASETSEMA2 Object = Agent Loc = Locto Time = Timeto INSTRUMENT [the same ASETSEMA subframes attached as by AGENT,

nly Object = Instrument,

which means that INSTRUMENT is supposed to move the same way as AGENT]

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 29

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Loc-Roles LOCFROM (starting place, e.g. from the garden, from under the table, from the box) Locfrom-in Locfrom-at LOC (where the motion takes place, e.g.

n the street,

in the garden, under the table) Loc-in Loc-at LOCTO (the ending place, e.g. onto the street, into the garden, into the box) Locto-in Locto-at

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 30

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Time-roles [The same system: TIMEFROM, TIME, TIMETO, DURATION] /---/ Other roles Not important in the given context: DIRECTON, PATH, MANNER, about 30 in total.

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 31

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Mary went from Tartu to Riga AGENTIVE SELF-MOTION HYPERONYM: MOTION AGENT = Mary FRAME: ASETSEMA1 [before] Object = Mary Loc = Tartu FRAME: ASETSEMA2 [after] Object = Mary Loc = Riga

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 32

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

John threw ball into the box AGENTIVE CAUSING MOTION HYPERONYM: MOTION AGENT = John FRAME: ASETSEMA1 [before] Object = John Loc = <previous> FRAME: ASETSEMA2 [after] Object = John Loc = <previous> FRAME: ASETSEMA1 [before] Object = ball Loc = <previous> FRAME: ASETSEMA2 [after] Object = ball Loc = box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 33

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 34

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 35

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 36

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 37

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 38

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 39

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 40

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Steps to Go

John threw ball into the box Where John was? John was here Where John is? John is here Where ball was? ball was here Where ball is? ball is in the box

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 41

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Summary

Morphological analysis and disambiguation Syntactic analysis and disambiguation Word sense disambiguation (?) Frames: From Framenet or our own? World knowledge Inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 42

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Summary

Morphological analysis and disambiguation Syntactic analysis and disambiguation Word sense disambiguation (?) Frames: From Framenet or our own? World knowledge Inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 43

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Summary

Morphological analysis and disambiguation Syntactic analysis and disambiguation Word sense disambiguation (?) Frames: From Framenet or our own? World knowledge Inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 44

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Summary

Morphological analysis and disambiguation Syntactic analysis and disambiguation Word sense disambiguation (?) Frames: From Framenet or our own? World knowledge Inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 45

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Summary

Morphological analysis and disambiguation Syntactic analysis and disambiguation Word sense disambiguation (?) Frames: From Framenet or our own? World knowledge Inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences

SLIDE 46

university-logo Motivation Steps to Go Frames and Semantic Roles Summary

Summary

Morphological analysis and disambiguation Syntactic analysis and disambiguation Word sense disambiguation (?) Frames: From Framenet or our own? World knowledge Inferences

Õim, Orav, Kahusk, Taremaa Semantic Analysis of Sentences