Automatic Recognition of the Function of Singular Neuter Pronouns in Texts and Spoken Data

Authors:
Costanza Navarretta
Affiliations:
Centre for Language Technology, University of Copenhagen, Copenhagen S, Denmark 2300
Venue:
DAARC '09 Proceedings of the 7th Discourse Anaphora and Anaphor Resolution Colloquium on Anaphora Processing and Applications
Year:
2009

Citing 11
Cited 1

Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging

Computational Linguistics
Assessing agreement on classification tasks: the kappa statistic

Computational Linguistics
A New, Fully Automatic Version of Mitkov's Knowledge-Poor Pronoun Resolution Method

CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
A Comparison of Rule-Based and Machine Learning Methods for Identifying Non-nominal It

NLP '00 Proceedings of the Second International Conference on Natural Language Processing
Resolving pronominal reference to abstract entities

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Improving machine learning approaches to coreference resolution

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
A machine learning approach to pronoun resolution in spoken dialogue

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Resolving individual and abstract anaphora in texts and dialogues

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Identifying non-referential it: a machine learning approach incorporating linguistically motivated patterns

FeatureEng '05 Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing
Disambiguation of the neuter pronoun and its effect on pronominal coreference resolution

TSD'07 Proceedings of the 10th international conference on Text, speech and dialogue

Predicting speech overlaps from speech tokens and co-occurring body behaviours in dyadic conversations

Proceedings of the 15th ACM on International conference on multimodal interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe the results of unsupervised (clustering) and supervised (classification) learning experiments with the purpose of recognising the function of singular neuter pronouns in Danish corpora of written and spoken language. Danish singular neuter pronouns comprise personal and demonstrative pronouns. They are very frequent and have many functions such as non-referential, cataphoric, deictic and anaphoric. The antecedents of discourse anaphoric singular neuter pronouns can be nominal phrases of different gender and number, verbal phrases, adjectival phrases, clauses or discourse segments of different size and they can refer to individual and abstract entities. Danish neuter pronouns occur in more constructions and have different distributions than the corresponding English pronouns it , this and that . The results of the classification experiments show a significant improvement of the performance with respect to the baseline in all types of data. The best results were obtained on text data, while the worst results were achieved on free-conversational, multi-party dialogues.