Date post: | 31-Dec-2015 |
Category: |
Documents |
Upload: | yoshio-beasley |
View: | 31 times |
Download: | 2 times |
04/19/23 1
Towards Semantics Generation
Third stage presentation of M.S project
Ashish Almeida
03M05601
Guide
Prof. Pushpak Bhattacharyya
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
04/19/23 3
Roadmap
• Problem
• UNL*
• Linguistic analysis
• Attachment solution
• Dictionary creation
• Implementation
• Conclusion
04/19/23 4
Current work (third stage)
• Organization of attributes
• Analysis of to-infinitive
• PRO-handling and resolution
• Acquisition of attributes for dictionary
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
04/19/23 6
UNL*
• UNL• UWs• Relations
John(icl>person)
give(icl>do)
Mary(iof>person)
flower(icl>flora)
agt golobj
@entry.@past
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
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.
04/19/23 9
Attachment algorithmFor Prepositional phrases
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:
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
04/19/23 12
UNL representationTheyi promised Mary [PROi to give a party].
04/19/23 13
Attachment algorithm tablefor to-infinitival clauses
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
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
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
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
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
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
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. …
04/19/23 21
from Penn Treebank• Syntactically annotated corpus • Example
• Algorithm to extract this property
04/19/23 22
Organizing attributes
• WordNet noun ontology explored.• The top level labels used as attributes.
• Example:
04/19/23 23
English to UNL system
• Rule base
Inputsentence
UNLexpression
Partial UNLexpression
WordNet OALD Penn tree-bank
04/19/23 24
Implementation
• POS Identification
• Finding Attachment site
• Creating Relation
• PRO insertion
• Post processing– Resolve the co-reference.
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
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;
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)
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)
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.
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
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
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
04/19/23 33
! Thank you