Towards Semantics Generation

33
06/12/22 1 Towards Semantics Generation Third stage presentation of M.S project Ashish Almeida 03M05601 Guide Prof. Pushpak Bhattacharyya

description

Towards Semantics Generation. Third stage presentation of M.S project Ashish Almeida 03M05601 Guide Prof. Pushpak Bhattacharyya. Motivation. Goal: semantic role labeling To commonly used functional element in English. (34% (source: Penn tree-bank)) - PowerPoint PPT Presentation

Transcript of Towards Semantics Generation

Page 1: Towards Semantics Generation

04/19/23 1

Towards Semantics Generation

Third stage presentation of M.S project

Ashish Almeida

03M05601

Guide

Prof. Pushpak Bhattacharyya

Page 2: Towards Semantics Generation

04/19/23 2

Motivation

• Goal: semantic role labeling

• To commonly used functional element in English. (34% (source: Penn tree-bank))

• To act as both preposition and as infinitival marker.

• PRO was not considered before in semantic labeling

Page 3: Towards Semantics Generation

04/19/23 3

Roadmap

• Problem

• UNL*

• Linguistic analysis

• Attachment solution

• Dictionary creation

• Implementation

• Conclusion

Page 4: Towards Semantics Generation

04/19/23 4

Current work (third stage)

• Organization of attributes

• Analysis of to-infinitive

• PRO-handling and resolution

• Acquisition of attributes for dictionary

Page 5: Towards Semantics Generation

04/19/23 5

Problem • Semantics generation for sentences involving

lexeme to • Three problems

– Identifying the proper part of speech (POS)– Attachment ambiguity resolution– Handling PRO

• FocusOnly [V-N-to-N/V] frames considered.Document specific dictionary used

Page 6: Towards Semantics Generation

04/19/23 6

UNL*

• UNL• UWs• Relations

John(icl>person)

give(icl>do)

Mary(iof>person)

flower(icl>flora)

agt golobj

@entry.@past

Page 7: Towards Semantics Generation

04/19/23 7

Differentiating POS

• Identify to-preposition phrase from to-infinitival clause

• … gave papers to the judge- to is followed by a determiner

• … increases to 25 million rupees- to is followed by a number

• … to cooks.- to is followed by a plural noun

Page 8: Towards Semantics Generation

04/19/23 8

Differentiating POS … to-infinitival

• …to go… - to is followed by a base verb

• … to clearly write…- to is followed by adverb followed by base verb.

Page 9: Towards Semantics Generation

04/19/23 9

Attachment algorithmFor Prepositional phrases

Page 10: Towards Semantics Generation

04/19/23 10

Example • John gave a flower to Mary.

– Verb gave expects to

– Noun flower does not expect to

– Apply case 3

– Attach ‘to Mary’ to gave • Final UNL:

Page 11: Towards Semantics Generation

04/19/23 11

To infinitival clauses

• Example

1a. He promised me [to come for the party]. 1b. Hei promised me [PROi to come for the party].

promise subject controlled pro

2a. They forced Mary [to give a party]. 2b. They forced Maryj [PROj to give a party].

force object controlled pro

Page 12: Towards Semantics Generation

04/19/23 12

UNL representationTheyi promised Mary [PROi to give a party].

Page 13: Towards Semantics Generation

04/19/23 13

Attachment algorithm tablefor to-infinitival clauses

Page 14: Towards Semantics Generation

04/19/23 14

PRO resolution

Example

a. He ordered us [to finish the work].

b. He ordered usi [PROi to finish the work].

Steps1. fetch PRO type fom dictionary entry of order2. Resolve all relations within clause

- [PROi to finish the work]

3. Relate the clause to verb order4. Finally replace the PRO with actual UW

Page 15: Towards Semantics Generation

04/19/23 15

Semantic relations

• Filled using the Levin’s verb classes.

• No semantically role resource available

• Stored in dictionary along with argument information

Page 16: Towards Semantics Generation

04/19/23 16

System

Resolve pro

Coindex the PRO

UNL expressions

Sentence having to

To-preposition

To-infinitive

Decide type and existence of PRO

Find semantic relation

Find attachment site

Find attachment site

Detect part of speech

Find semantic relation

Page 17: Towards Semantics Generation

04/19/23 17

Dictionary

• All words must be present in dictionary

• Structure[letter] “letter(icl>document)” (N,INANI,PHSCL) <E,0,0>

headword Universal word Attributes

Page 18: Towards Semantics Generation

04/19/23 18

Dictionary: Acquisition of attributes

New attribute needed to apply the algorithm• Argument structure information• Semantic relations • PRO control property of verbs

• Oxford, WordNet• Penn Treebank• Beth Levin’s verb classification

Page 19: Towards Semantics Generation

04/19/23 19

from WordNet

• Sentence frames for verbs• Example• For verb want

– They ____ him to write the letter. For the verb promise– Somebody ----s somebody to INFINITIVE

Page 20: Towards Semantics Generation

04/19/23 20

from Oxford dictionary

• Oxford advanced learners dictionary (OALD)

provides partial frames wherever applicable• Examples

effort noun

…… 2 [C] ~ (to do sth) an attempt to do sth especially when it is difficult to do: to make a determined / real / special effort to finish on time …..

force verb

make sb do sth 1 [often passive] ~ sb (into sth / into doing sth) to make sb do sth that they do not want to do SYN COMPEL …• [VN to inf] I was forced to take a taxi because the last bus had left. • She forced herself to be polite to them. …

Page 21: Towards Semantics Generation

04/19/23 21

from Penn Treebank• Syntactically annotated corpus • Example

• Algorithm to extract this property

Page 22: Towards Semantics Generation

04/19/23 22

Organizing attributes

• WordNet noun ontology explored.• The top level labels used as attributes.

• Example:

Page 23: Towards Semantics Generation

04/19/23 23

English to UNL system

• Rule base

Inputsentence

UNLexpression

Partial UNLexpression

WordNet OALD Penn tree-bank

Page 24: Towards Semantics Generation

04/19/23 24

Implementation

• POS Identification

• Finding Attachment site

• Creating Relation

• PRO insertion

• Post processing– Resolve the co-reference.

Page 25: Towards Semantics Generation

04/19/23 25

Identification of POSPattern to detect to infinitive:

-to followed by verb in base form

:{:::}{^TO_INF_NEXT:+TO_INF_NEXT::}(#TO,TO_INF)(BLK)(VRB,V_1)P40;

IF (The left analysis window (indicated by {}) is on any word) AND (The right analysis window is on a word which does not have a TO_INF_NEXT i.e.

look ahead is not performed yet. )THEN

Select the next sequence of words such that they will satisfy the conditions as – pick the word to corresponding to infinitival-to (indicated by attributes #TO and TO_INF) AND pick a space (indicated as BLK) AND pick a verb which is in its simple form (indicated by V_1) AND add the property TO_INF_NEXT to the word in the right analysis window

Page 26: Towards Semantics Generation

04/19/23 26

Attachment rules

• Do noun attachment – Move ahead when on frame [V][N]-P-N

R{VRB,#_TO_AR2:::}{N,#_TO:::}(PRE,#TO)P60;

• Create goal relation – gol(uw1, uw2)

<{VRB,#_TO_AR2,#_TO_AR2_gol:::}

{N,TORES,PRERES::gol:}P25;

Page 27: Towards Semantics Generation

04/19/23 27

Handling PRO

1. Produce a “PRO” element in UNL with appropriate relation. (Enconverter) :{VRB,SUB_PRO:::}"[[SUB_PRO]]:N,SUB_PRO,

#INSERTED::"(VRB,TO_INFRES,^PRORES)P30;

2. Relate it to the verb of the infinitive clause semantically. (Enconverter) >(VRB){N,SUB_PRO::agt:}{VRB,VOA,TO_INFRES:

+PRORES,+SUB_PRORES::}P40;

3. Substitute a referred UW in the place of PRO. (Post editor)

Page 28: Towards Semantics Generation

04/19/23 28

Replace PROExample

They promised Maryi [PROi to give a party].

agt (promise(icl>do).@entry.@past, they:0A)gol (promise(icl>do).@entry.@past, Mary(iof>person))obj (promise(icl>do), :01)agt :01(give(icl>do), sub_PRO:0C)obj :01(give(icl>do), party(icl>function))

After post processing

agt :01(give(icl>do), they:0A)

Page 29: Towards Semantics Generation

04/19/23 29

Evaluation

• Preparation of test sentences

• Source : Penn Treebank, edict concordencer and Oxford

• Dictionary – Automatic dictionary generator– Editing and corrections– Appending extra attributes.

Page 30: Towards Semantics Generation

04/19/23 30

ResultsTo Prepositio

n senseInfinitiv

esense

Total number of sentences(200) 100 100

Number of sentences where correct sense of to is detected

97 93

Number of sentences with correct attachment/UNL

80 72

Page 31: Towards Semantics Generation

04/19/23 31

Conclusion

• Automatic acquisition of attributes is effective.

• Correct Semantic representation is crucial.– Helps in applications like information retrival,

generation to other language, question answering

Page 32: Towards Semantics Generation

04/19/23 32

References• Grimshaw, Jane: Argument Structure. The MIT Press, Cambridge,

Mass. (1990)

• Mohanty R.K., Almeida A., Srinivas S., Bhattacharyaa P.: The complexity of OF, ICON, Hydrabad, India. (2004)

• UNDL Foundation: The Universal Networking Language (UNL) specifications version 3.2. (2003) http://www.unlc.undl.org

• Resources– OALD– WordNet– Penn Tree bank– DDG– Concordance search on Brown corpus– Beth Levin’s verb classes

Page 33: Towards Semantics Generation

04/19/23 33

! Thank you