Anaphora resolution, collocations and translation
-
Eric Wehrli
Abstract
Collocation identification and anaphora resolution are widely recognised as major issues for natural language processing, and particularly for machine translation. This paper focuses on their intersection domain, that is verb-object collocations in which the object has been pronominalised. To handle such cases, an anaphora resolution procedure must link the direct object pronoun to its antecedent. The identification of a collocation can then be made on the basis of the verb and its object or its antecedent. Results obtained from the translation of a large corpus will be discussed, as well as an evaluation of the precision of the anaphora resolution procedure for this specific task.
Abstract
Collocation identification and anaphora resolution are widely recognised as major issues for natural language processing, and particularly for machine translation. This paper focuses on their intersection domain, that is verb-object collocations in which the object has been pronominalised. To handle such cases, an anaphora resolution procedure must link the direct object pronoun to its antecedent. The identification of a collocation can then be made on the basis of the verb and its object or its antecedent. Results obtained from the translation of a large corpus will be discussed, as well as an evaluation of the precision of the anaphora resolution procedure for this specific task.
Kapitel in diesem Buch
- Prelim pages i
- Table of contents v
- About the editors vii
- Multiword units in machine translation and translation technology 1
-
Part 1. Multiword units in machine translation
- Analysing linguistic information about word combinations for a Spanish-Basque rule-based machine translation system 41
- How do students cope with machine translation output of multiword units? An exploratory study 61
- Aligning verb + noun collocations to improve a French-Romanian FSMT system 81
-
Part 2. Multiword units in multilingual NLP applications
- Multiword expressions in multilingual information extraction 103
- A multilingual gold standard for translation spotting of German compounds and their corresponding multiword units in English, French, Italian and Spanish 125
- Dutch compound splitting for bilingual terminology extraction 147
-
Part 3. Identification and translation of multiword units
- A flexible framework for collocation retrieval and translation from parallel and comparable corpora 165
- On identification of bilingual lexical bundles for translation purposes 181
- The quest for croatian idioms as multiword units 201
- Corpus analysis of croatian constructions with the verb doći ‘to come’ 223
- Anaphora resolution, collocations and translation 243
- Index 257
Kapitel in diesem Buch
- Prelim pages i
- Table of contents v
- About the editors vii
- Multiword units in machine translation and translation technology 1
-
Part 1. Multiword units in machine translation
- Analysing linguistic information about word combinations for a Spanish-Basque rule-based machine translation system 41
- How do students cope with machine translation output of multiword units? An exploratory study 61
- Aligning verb + noun collocations to improve a French-Romanian FSMT system 81
-
Part 2. Multiword units in multilingual NLP applications
- Multiword expressions in multilingual information extraction 103
- A multilingual gold standard for translation spotting of German compounds and their corresponding multiword units in English, French, Italian and Spanish 125
- Dutch compound splitting for bilingual terminology extraction 147
-
Part 3. Identification and translation of multiword units
- A flexible framework for collocation retrieval and translation from parallel and comparable corpora 165
- On identification of bilingual lexical bundles for translation purposes 181
- The quest for croatian idioms as multiword units 201
- Corpus analysis of croatian constructions with the verb doći ‘to come’ 223
- Anaphora resolution, collocations and translation 243
- Index 257
