270 likes | 727 Views
Prepositional Phrase Attachment Problem. 03M05601 Ashish Almeida. Overview. Introduction to NLP Analysis in UNL system Prepositional phrase attachment problem Proposed method to handle this problem. Motivation. Analysis involves many complex problems
E N D
Prepositional Phrase Attachment Problem 03M05601 Ashish Almeida PP attachment problem
Overview • Introduction to NLP • Analysis in UNL system • Prepositional phrase attachment problem • Proposed method to handle this problem PP attachment problem
Motivation • Analysis involves many complex problems • Prepositional phrase attachment problem is one such difficult problem. • If solved, improve the quality of information extracted manifold • No existing system solves the problem PP attachment problem
NL understanding Text Meaning NL generation Tasks involved in NLP Analysis and generation PP attachment problem
Phases in NLP • Morphological analysis • Syntactic analysis • Semantic analysis • Discourse integration • Pragmatic analysis PP attachment problem
Is NL Compositional ? • Compsitional expression • Meaning of the whole from meaning of parts e.g. strong tea -rich tea day by day - all the time PP attachment problem
Analysis Morphological + Syntactic + Semantic analysis • All these phases are dependent on each other. • Interactive Vs modular approach • Analysis in UNL system - interactive PP attachment problem
UNL … • UNL is Interlingua e.g. Ram ate rice with spoon. eat(icl>do) @ entry @ present agt ins obj John(iof>person) spoon(icl>artifact) rice(icl>food) PP attachment problem
UNL expresion UNL Expression for Ram ate rice with spoon. agt(eat(icl>do).@past.@entry, Ram(iof>person)) obj(eat(icl>do).@past.@entry, rice(icl>food)) ins(eat(icl>do).@past.@entry, spoon(icl>tool)) agt(eat(icl>do).@past.@entry, Ram(iof>person)) Relation UWs Attributes PP attachment problem
Analysis in UNL • Enconverter • Natural Language to UNL • Handles one sentence at a time • Predicate preserving parser • Kind of Turing machine • Components • Dictionary : lexical units, uw, semantic attributes • Rule base : head movement rules, relation resolving rules • Working • Uses dictionary and rule bases to process the sentence. PP attachment problem
Prepositional Phrase Attachment Problem • Type of Structural ambiguity in a sentence Verb attachment JohnNP readVP the reportNP on new technologies.PP Noun attachment PP attachment problem
read read John the report John on the report on new technologies new technologies Prepositional Phrase Attachment Problem… • Noun attachment Vs verb attachment e.g. John read the report on new technologies. * PP attachment problem
Establishing semantic relation Same structure-different semantic relation e.g. 1. Ram ate rice withspoon.……instrument The UNL for this sentence is ins(eat(icl>do).@past.@entry, spoon(icl>tool)) 2. Ram ate rice with Sita. ……co-agent The UNL for this sentence is cag(eat(icl>do).@past.@entry, Sita(iof>person)) PP attachment problem
Difficult problem • PP attachment problem is simpler or no problem for human being - who use world knowledge to process it. • This world knowledge is not available to machines. e.g. travel by night …time travel by bus …instrument PP attachment problem
Different sites of attachment • The searchforthe policy is going on. • The test will be held at the endofAugust. • InAugust 1947, India became free from British rule. • Wilson received a medal from the commanding officerata farewell party. • There is no restriction on how far the PP can lie from the word to which it relates. PP attachment problem
Affinity with preceding phrase • The preposition ofgets attached to a noun phrase or a verb phrase immediately preceding it. • They were involved in the murder of a 90-year-old woman. • It was begun last week by the crew of a giant crane-barge. • He died of an overdose of sleeping pills • The system will be tailored to meet the need of the political party. PP attachment problem
Existing methods • generate mod-obj combination for almost all PP relations • E.g He came according to his promise. agt(come(icl>do)@past.@entry, he) *mod(come(icl>do)@past.@entry, :01) obj:01(according to, promise(icl>abstract thing)) mod:01(promise(icl>abstract thing),he) • Tags introduced manually to resolve phrase boundaries • E.g. It delineates <p>the scope of phrases</p> before <p>conversion of the sentence</p>. PP attachment problem
Related work • Statistical learning methods used • Wordnet is used to find relations between words • Analysis of corpus is required • Not all aspects of problem considered • The hypothesis does not apply to all cases “PP attachments obey the principle of locality” PP attachment problem
Frequency Preposition Poly. count 29391 of 7 18214 in 10 9343 to 8 14 by way of 1 16 by means of 1 Observations • Prepositions frequency is calculated from British National Corpus • Classified into 2 parts • Simple Preposition • Ambiguous prepositions PP attachment problem
Addition to Semantic Attributes hierarchy • Semantic attributes required to disambiguate • Addition required, if existing attributes fail to classify • necessary condition • the attributes should be able to classify the semantically separate structures as separate entities. e.g.the train for Delhi ….to() the price for the Hill Road pool ….mod() PP attachment problem
Inclusion of preposition in UNL expression • a picture on the wall plc(picture, wall). • The cat walked across the street. • Wrong UNL *plc ( walk, street ) -cat walked along the street -cat walked across the street • Correct UNL plc (walk, :01) obj:01(across, street) PP attachment problem
[ Verb + for + Noun phrase] v-pur He was waiting for the rainy day. v-pur He applied for a certificate. [ Noun phrase + for + Noun phrase] n-mod The search for the policy is going on. n-mod He pays the price for his indulgence. Classification based on syntax structure • Sentences have different syntactic structure • Parsing the depends on surface structure - Active-passive, transitive-di-transitive, present-past participles etc. • Classification based on syntax pattern PP attachment problem
Relation Example sentence ON plc a picture on a wall ins to travel on the bus tim He came on Sunday seq Report to reception on arrival mod a book on South Africa ins She played a tune on her guitar plc You can get me on 0181 530 3906 Classification based on semantics • Deciding factors • Syntax, attributes, preposition, subcategorisation frame(for verbs) Partial list of preposition on and its possible semantic relation PP attachment problem
Comment ;N/abs for N/abs ;search for policy delete preposition for DL(N,ABS) {PRE,#FOR:::} {N,ABS:+PRERES,+FORRES,+pPUR::}P25; Comment ;V FOR N-UNIT-QUARES ;suspend for 2 days Delete preposition for DL(VRB){PRE,#FOR:::} {N,UNIT,TIM,QUARES :+PRERES,+FORRES,+pDUR::}P30; Updating rule base • Simpler if the classification is perfect. • Issues involved • Priority, proper specification Two rules showing difference in priority – specific to general PP attachment problem
Conclusion • World knowledge is realized in terms of semantic attributes. • Phrasal verbs are not considered • Idiomatic constructs are not handled - e.g. day by day all the time PP attachment problem