Dialog Act Classification Using N-Gram Algorithms

Max Louwerse, Scott Crossley

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

19 Citations (Scopus)

Abstract

Speech act classification remains one of the challenges in natural language processing. This paper evaluates a classification system that assigns one of twelve dialog acts to an utterance from the Map Task Corpus. The dialog act classification system chooses a dialog act based on n-grams form a training set. The system's performance is comparable to other classification systems, like those using support vector machines. Performance is high given the fact that the system only considers an utterance out of context and from written input only. Moreover, the system's performance is on par with human performance.
Original languageEnglish
Title of host publicationProceedings of the 19th International Florida Artificial Intelligence Research Society Conference
EditorsGeoff Sutcliffe, Randy Goebel
Place of PublicationMenlo Park
PublisherAAAI Press
Pages758-763
Publication statusPublished - 2006
Externally publishedYes
Event19th International Florida Artificial Intelligence Research Society Conference - Melbourne Beach, United States
Duration: 11 May 200613 May 2006

Conference

Conference19th International Florida Artificial Intelligence Research Society Conference
CountryUnited States
CityMelbourne Beach
Period11/05/0613/05/06

Fingerprint Dive into the research topics of 'Dialog Act Classification Using N-Gram Algorithms'. Together they form a unique fingerprint.

  • Cite this

    Louwerse, M., & Crossley, S. (2006). Dialog Act Classification Using N-Gram Algorithms. In G. Sutcliffe, & R. Goebel (Eds.), Proceedings of the 19th International Florida Artificial Intelligence Research Society Conference (pp. 758-763). AAAI Press. https://pdfs.semanticscholar.org/0878/2e1bf9cac6c255a17f766809b135c910e018.pdf