Output details
11 - Computer Science and Informatics
Manchester Metropolitan University
Return to search
Output 0 of 0 in the submission
Article title
A multi-classifier approach to dialogue act classification using function words
Type
D - Journal article
Title of journal
Transactions on Computational Collective Intelligence VII. Lecture Notes in Computer Science.
Article number
-
Volume number
7270
Issue number
-
First page of article
119
ISSN of journal
1611-3349
Year of publication
2012
URL
-
Number of additional authors
2
Additional information
<22>This paper extends a novel technique for the classification of sentences as Dialogue Acts (DA), based on structural information contained in function words. Its novelty arises from rejecting the assumption that function words do not contribute to semantic similarity. Instead, it proposes that it is possible to classify short texts into high-level DA categories by using function words alone. This supports the construction of computationally efficient decision tree classifiers through machine learning, which should scale well in web-based agents.
Interdisciplinary
-
Cross-referral requested
-
Research group
B - Computational Intelligence and Reasoning
Citation count
0
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
