Corpus-based and machine learning approaches to anaphora resolution
-
Michael Strube
Abstract
Anaphora resolution is an important component of natural language processing applications like information extraction, question answering, or automatic summarization. These applications have to deal with unrestricted input which is difficult to process with symbolic anaphora resolution methods. If trained on unrestricted input, machine learning based anaphora resolution methods can robustly deal with a wide variety of input documents. Those methods are mostly implemented as binary classification realizing models of local inference. While this makes the task accessible to standard machine learning techniques, it has the drawback that knowledge about the context is lost. Based on a critical assessment of the state-of-the-art, models of global inference are introduced as a possible alternative.
Abstract
Anaphora resolution is an important component of natural language processing applications like information extraction, question answering, or automatic summarization. These applications have to deal with unrestricted input which is difficult to process with symbolic anaphora resolution methods. If trained on unrestricted input, machine learning based anaphora resolution methods can robustly deal with a wide variety of input documents. Those methods are mostly implemented as binary classification realizing models of local inference. While this makes the task accessible to standard machine learning techniques, it has the drawback that knowledge about the context is lost. Based on a critical assessment of the state-of-the-art, models of global inference are introduced as a possible alternative.
Chapters in this book
- Prelim pages i
- Table of contents v
- Anaphors in text – Introduction vii
-
Anaphors in Cognitive, Text- and Discourse Linguistics
- Indirect anaphora in text 3
- Indirect pronominal anaphora in English and French 21
- Lexical anaphors in Danish and French 37
- Referential collaboration with computers 49
- Reflexivity and temporality in discourse deixis 69
- The function of complex anaphors in texts 81
- Metaphorical anaphors 103
-
The Syntax and Semantic of Anaphors
- Accessibility and definite noun phrases 123
- The non-subject bias of German demonstrative pronouns 145
- Anaphoric properties of German right dislocation 165
- Antecedents of diverse types 183
- Corpus-based and machine learning approaches to anaphora resolution 207
-
Neurolinguistic Studies
- Neuroimaging studies of coherence processes 225
- Reference assignment in the absence of sufficient semantic content 241
- Resolving complex anaphors 259
- Index 279
Chapters in this book
- Prelim pages i
- Table of contents v
- Anaphors in text – Introduction vii
-
Anaphors in Cognitive, Text- and Discourse Linguistics
- Indirect anaphora in text 3
- Indirect pronominal anaphora in English and French 21
- Lexical anaphors in Danish and French 37
- Referential collaboration with computers 49
- Reflexivity and temporality in discourse deixis 69
- The function of complex anaphors in texts 81
- Metaphorical anaphors 103
-
The Syntax and Semantic of Anaphors
- Accessibility and definite noun phrases 123
- The non-subject bias of German demonstrative pronouns 145
- Anaphoric properties of German right dislocation 165
- Antecedents of diverse types 183
- Corpus-based and machine learning approaches to anaphora resolution 207
-
Neurolinguistic Studies
- Neuroimaging studies of coherence processes 225
- Reference assignment in the absence of sufficient semantic content 241
- Resolving complex anaphors 259
- Index 279
