Presentation is loading. Please wait.

Presentation is loading. Please wait.

Towards Semantics Generation

Similar presentations


Presentation on theme: "Towards Semantics Generation"— Presentation transcript:

1 Towards Semantics Generation
Third stage presentation of M.S project Ashish Almeida 03M05601 Guide Prof. Pushpak Bhattacharyya 2/17/2019

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 2/17/2019

3 Roadmap Problem UNL* Linguistic analysis Attachment solution
Dictionary creation Implementation Conclusion 2/17/2019

4 Current work (third stage)
Organization of attributes Analysis of to-infinitive PRO-handling and resolution Acquisition of attributes for dictionary 2/17/2019

5 Problem Semantics generation for sentences involving lexeme to
Three problems Identifying the proper part of speech (POS) Attachment ambiguity resolution Handling PRO Focus Only [V-N-to-N/V] frames considered. Document specific dictionary used 2/17/2019

6 flower(icl>flora)
UNL* give(icl>do) gol agt obj John(icl>person) Mary(iof>person) flower(icl>flora) UNL UWs Relations 2/17/2019

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 2/17/2019

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. 2/17/2019

9 Attachment algorithm For Prepositional phrases 2/17/2019

10 Example John gave a flower to Mary. Final UNL: Verb gave expects to
Noun flower does not expect to Apply case 3 Attach ‘to Mary’ to gave Final UNL: 2/17/2019

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 2/17/2019

12 UNL representation Theyi promised Mary [PROi to give a party].
2/17/2019

13 Attachment algorithm table
for to-infinitival clauses 2/17/2019

14 PRO resolution Example a. He ordered us [to finish the work].
b. He ordered usi [PROi to finish the work]. Steps fetch PRO type fom dictionary entry of order Resolve all relations within clause - [PROi to finish the work] Relate the clause to verb order Finally replace the PRO with actual UW 2/17/2019

15 Semantic relations Filled using the Levin’s verb classes.
No semantically role resource available Stored in dictionary along with argument information 2/17/2019

16 System Sentence having to Detect part of speech Find attachment site
To-infinitive To-preposition Find attachment site Decide type and existence of PRO Find attachment site Resolve pro Find semantic relation Find semantic relation Coindex the PRO UNL expressions 2/17/2019

17 Dictionary All words must be present in dictionary Structure
[letter] “letter(icl>document)” (N,INANI,PHSCL) <E,0,0> headword Universal word Attributes 2/17/2019

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 2/17/2019

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 2/17/2019

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. … 2/17/2019

21 from Penn Treebank Syntactically annotated corpus Example
Algorithm to extract this property 2/17/2019

22 Organizing attributes
WordNet noun ontology explored. The top level labels used as attributes. Example: 2/17/2019

23 English to UNL system Enconverter Post editor Rule base WordNet OALD
Partial UNL expression UNL expression Input sentence Enconverter Post editor WordNet OALD Penn tree-bank Rule base 2/17/2019

24 Implementation POS Identification Finding Attachment site
Creating Relation PRO insertion Post processing Resolve the co-reference. 2/17/2019

25 Identification of POS Pattern 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 2/17/2019

26 Attachment rules Do noun attachment Create goal relation
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; 2/17/2019

27 Handling PRO 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) 2/17/2019

28 Replace PRO Example They promised Maryi [PROi to give a party].
agt they:0A) gol 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) 2/17/2019

29 Evaluation Preparation of test sentences
Source : Penn Treebank, edict concordencer and Oxford Dictionary Automatic dictionary generator Editing and corrections Appending extra attributes. 2/17/2019

30 Results To Preposition sense Infinitive sense
Total number of sentences(200) 100 Number of sentences where correct sense of to is detected 97 93 Number of sentences with correct attachment/UNL 80 72 2/17/2019

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 2/17/2019

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) Resources OALD WordNet Penn Tree bank DDG Concordance search on Brown corpus Beth Levin’s verb classes 2/17/2019

33 ! Thank you 2/17/2019


Download ppt "Towards Semantics Generation"

Similar presentations


Ads by Google