1 / 33

Towards Semantics Generation

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))

Download Presentation

Towards Semantics Generation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


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

  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

  3. Roadmap • Problem • UNL* • Linguistic analysis • Attachment solution • Dictionary creation • Implementation • Conclusion

  4. Current work (third stage) • Organization of attributes • Analysis of to-infinitive • PRO-handling and resolution • Acquisition of attributes for dictionary

  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

  6. UNL* give(icl>do) @entry.@past • UNL • UWs • Relations gol agt obj John(icl>person) Mary(iof>person) flower(icl>flora)

  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

  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.

  9. Attachment algorithm For Prepositional phrases

  10. Example • John gave a flower to Mary. • Verb gave expects to • Noun flowerdoes not expect to • Apply case 3 • Attach ‘to Mary’ to gave • Final UNL:

  11. To infinitival clauses • Example 1a. He promised me [to come for the party]. 1b. Heipromised me [PROito 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

  12. UNL representation Theyi promised Mary [PROi to give a party].

  13. Attachment algorithm table for to-infinitival clauses

  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

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

  16. System Sentence having to Detect part of speech 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

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

  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

  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

  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. …

  21. from Penn Treebank • Syntactically annotated corpus • Example • Algorithm to extract this property

  22. Organizing attributes • WordNet noun ontology explored. • The top level labels used as attributes. • Example:

  23. English to UNL system Partial UNL expression • Rule base UNL expression Input sentence Enconverter Post editor WordNet OALD Penn tree-bank

  24. Implementation • POS Identification • Finding Attachment site • Creating Relation • PRO insertion • Post processing • Resolve the co-reference.

  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

  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;

  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)

  28. Replace PRO Example They promised Maryi [PROito 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)

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

  30. Results

  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

  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

  33. ! Thank you

More Related