Automatic Extraction of Cue Phrases for Cross-Corpus Dialogue Act Classification
نویسندگان
چکیده
In this paper, we present an investigation into the use of cue phrases as a basis for dialogue act classification. We define what we mean by cue phrases, and describe how we extract them from a manually labelled corpus of dialogue. We describe one method of evaluating the usefulness of such cue phrases, by applying them directly as a classifier to unseen utterances. Once we have extracted cue phrases from one corpus, we determine if these phrases are general in nature, by applying them directly as a classification mechanism to a different corpus to that from which they were extracted. Finally, we experiment with increasingly restrictive methods for selecting cue phrases, and demonstrate that there are a small number of core cue phrases that are useful for dialogue act classification.
منابع مشابه
Cue-based dialogue act classification
Cue-Based Dialogue Act Classification Nick Webb Supervisors: Yorick Wilks & Mark Hepple In this thesis, we will address three research questions relating to the discovery and use of cue phrases for Dialogue Act classification. Cue phrases are single words, or combinations of words in phrases, that can serve as reliable indicators of some discourse function. In our case, we are looking to automa...
متن کاملInvestigating the Portability of Corpus-Derived Cue Phrases for Dialogue Act Classification
We present recent work in the area of Cross-Domain Dialogue Act tagging. Our experiments investigate the use of a simple dialogue act classifier based on purely intra-utterance features principally involving word n-gram cue phrases. We apply automatically extracted cues from one corpus to a new annotated data set, to determine the portability and generality of the cues we learn. We show that ou...
متن کاملInstitute of Informatics Logics and Security Studies Automatic Extraction of Cues Phrases for Cross-Corpus Dialogue Act Classification
متن کامل
Dialogue Act Recognition using Cue Phrases
Dialogue acts play an important role in modelling discourse phenomena in several components of modern dialogue systems. Many different features have been so far proposed for dialogue act recognition. In this report, we take a cue-based model approach, and use N grams in utterances in dialogue as cue phrases. In our experiment with the switchboard corpus, we obtained 57.1% classification accurac...
متن کاملCross-Domain Dialogue Act Tagging
We present recent work in the area of Cross-Domain Dialogue Act (DA) tagging. We have previously reported on the use of a simple dialogue act classifier based on purely intra-utterance features — principally involving word n-gram cue phrases automatically generated from a training corpus. Such a classifier performs surprisingly well, rivalling scores obtained using far more sophisticated langua...
متن کامل