CSCI 5832 Natural Language Processing Jim Martin Lecture 23 4 15 08 1 Today 4 15 Discourse structure Referring expressions Co reference resolution 2 4 15 08 What Makes a Discourse Coherent The reason is that these utterances when juxtaposed will not exhibit coherence Almost certainly not Do you have a discourse Assume that you have collected an arbitrary set of wellformed and independently interpretable utterances for instance by randomly selecting one sentence from each of the previous chapters of this book 3 4 15 08 1 Better Assume that you have collected an arbitrary set of well formed and independently interpretable utterances for instance by randomly selecting one sentence from each of the previous chapters of this book Do you have a discourse Almost certainly not The reason is that these utterances when juxtaposed will not exhibit coherence 4 4 15 08 What makes a text coherent Appropriate use of coherence relations between subparts of the discourse rhetorical structure Appropriate sequencing of subparts of the discourse discourse topic structure Appropriate use of referring expressions 5 4 15 08 Referring Expressions Referring expressions provide a kind of glue that makes texts cohere 6 4 15 08 2 Referring Expressions Definition Referring expressions are words or phrases the semantic interpretation of which is a discourse entity also called referent Discourse entities are semantic objects and they can have multiple syntactic realizations within a text 7 4 15 08 NY Times Example A college student accused of faking her own kidnapping last month was charged Wednesday with lying to police in what they suggested was a desperate attempt to get her boyfriend s attention Audrey Seiler a 20 year old sophomore at the University of Wisconsin was charged with two misdemeanor counts of obstructing officers Each charge carries up to nine months in jail and a 10 000 fine Seiler disappeared from her off campus apartment March 27 without her coat or purse She was discovered curled in a fetal position in a marsh four days later and told police that a man had abducted her at knifepoint But police concluded Seiler made up the story after obtaining a store videotape that showed her buying the knife duct tape rope and cold medicine she claimed her abductor used to restrain her Seiler confessed after she was confronted with the tape according to authorities 8 4 15 08 Referring Expressions Example A pretty woman entered the restaurant She sat at the table next to mine and only then I recognized her This was Amy Garcia my next door neighbor from 10 years ago The woman has totally changed Amy was at the time shy 9 4 15 08 3 Pronouns vs Full NPs A pretty woman entered the restaurant She sat at the table next to mine and only then I recognized her This was Amy Garcia my next door neighbor from 10 years ago The woman has totally changed Amy was at the time shy 10 4 15 08 Definite vs Indefinite NPs A pretty woman entered the restaurant She sat at the table next to mine and only then I recognized her This was Amy Garcia my next door neighbor from 10 years ago The woman has totally changed Amy was at the time shy 11 4 15 08 Common Noun vs Proper Noun A pretty woman entered the restaurant She sat at the table next to mine and only then I recognized her This was Amy Garcia my next door neighbor from 10 years ago The woman has totally changed Amy was at the time shy 12 4 15 08 4 Modified vs Bare head NP A pretty woman entered the restaurant She sat at the table next to mine and only then I recognized her This was Amy Garcia my next door neighbor from 10 years ago The woman has totally changed Amy was at the time shy 13 4 15 08 Premodified vs postmodified A pretty woman entered the restaurant She sat at the table next to mine and only then I recognized her This was Amy Garcia my next door neighbor from 10 years ago The woman has totally changed Amy was at the time shy 14 4 15 08 More NP types Inferrables Sally bought a used car The tires need to be replaced Discontinuous sets John has known Bill for many years now They often go hiking together 15 4 15 08 5 Break Quiz Thursday Then Q A and Summarization Read Chapter 23 for Tuesday MT Read Chapter 25 for the following Thursday 16 4 15 08 Quiz Areas From 17 Basics of FOL Syntax and semantics From 18 Rule to rule approach Semantic attachments Lambdas Problems with quantifiers From 20 Different approaches to WSD 20 1 to 20 5 17 4 15 08 Quiz Areas From 21 21 3 to 21 8 Focus on Hobbs and ML approaches in 21 6 1 and 21 6 3 for pronominal resolution From 22 All 18 4 15 08 6 Quiz Don t forget all the earlier stuff In particular syntax parsing plays a big role in Semantic analysis Co reference And it plays a supporting role in IE and WSD Provides features 19 4 15 08 Anaphora resolution Finding in a text all the referring expressions that have one and the same denotation Pronominal anaphora resolution Anaphora resolution between named entities Full noun phrase anaphora resolution Zero anaphora detection resolution 20 4 15 08 Automatic Anaphora Resolution Resolving the referents of pronouns Hand built rule systems vs trained systems Statistical systems vs rules Systems that require a full syntactic parse vs systems that assume a weaker chunking segmentation Systems that deal with text vs systems that deal with spoken discourse 21 4 15 08 7 Basic ML Approach for Pronominal Reference Acquire an annotated corpus Pronoun antecedent pairs constitute examples Pronoun non referent pairs are examples Lots more data than data Extract features from the pairs Train a binary classifier SVMs or MaxEnt 22 4 15 08 Basic Features Strict grammatical number match 1 0 Not the number of the elements just whether they match Compatible match Same 2 for gender Sentence distance Distance from pronoun sentence to the referent Hobbs distance Grammatical role information Form Form of the antecedent full NP etc 23 4 15 08 Classification Proceed through a text linearly When a pronoun is encountered look backward and apply the classifier to each potential antecedent In some order Need a way to break ties Result is a set of referent chains 24 4 15 08 8 Full Co reference Analysis Locating all the entity mentions in a text and then clustering them into groups that represent the actual entities 25 4 15 08 NY Times Example A college student accused of faking her own kidnapping last month was charged Wednesday with lying to police in what they suggested was a desperate attempt to get her boyfriend s
View Full Document
Unlocking...