A computational theory of grounding in natural language conversation
A computational theory of grounding in natural language conversation
Assessing agreement on classification tasks: the kappa statistic
Computational Linguistics
A maximum entropy approach to natural language processing
Computational Linguistics
Wrappers for feature subset selection
Artificial Intelligence - Special issue on relevance
A simple, fast, and effective rule learner
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Utterance Units in Spoken Dialogue
ECAI '96 Workshop on Dialogue Processing in Spoken Language Systems
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
Non-sentential utterances in dialogue: a corpus-based study
SIGDIAL '02 Proceedings of the 3rd SIGdial workshop on Discourse and dialogue - Volume 2
Learning to resolve bridging references
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Classifying ellipsis in dialogue: a machine learning approach
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Classifying Non-Sentential Utterances in Dialogue: A Machine Learning Approach
Computational Linguistics
Hi-index | 0.00 |
Non-sentential utterances (e.g., short-answers as in "Who came to the party?"--- "Peter.") are pervasive in dialogue. As with other forms of ellipsis, the elided material is typically present in the context (e.g., the question that a short answer answers). We present a machine learning approach to the novel task of identifying fragments and their antecedents in multiparty dialogue. We compare the performance of several learning algorithms, using a mixture of structural and lexical features, and show that the task of identifying antecedents given a fragment can be learnt successfully (f(0.5) = .76); we discuss why the task of identifying fragments is harder (f(0.5) = .41) and finally report on a combined task (f(0.5) = .38).