Implementation and performance exploration of a cross-genre part of speech tagging methodology to determine dialog act tags in the chat domain
Martell, Craig H.
Young, Joel D.
MetadataShow full item record
Internet Relay Chat is a popular means of communication. Because chat data does not follow established grammatical rules, traditional machine learning algorithms perform poorly in tasks such as part-of-speech and dialog-act tagging, and yet the volume of data created makes human analysis impractical. We present a cross-genre part-of-speech tagging methodology and analyze its effectiveness in determining the dialog-act classes of chat posts. Previous methods for determining part-of-speech tags focused on accuracy, were computationally expensive and required human verification. We show that our cross-genre maximum likelihood estimation part-of-speech tagging performs virtually identically to hand-tagged parts-of-speech and that accurate part-of-speech tags are not required for acceptable automatic dialog-act determination. Furthermore, we show that a simple naÄ±ve Bayes classifier achieves the same performance in a fraction of the time as a carefully trained neural network.
Approved for public release; distribution is unlimited
Showing items related by title, author, creator and subject.
Forsyth, Eric N. (Monterey, California. Naval Postgraduate School, 2007-09);One of the goals of natural language processing (NLP) systems is determining the meaning of what is being transmitted. Although much work has been accomplished in traditional written and spoken language domains, little has ...
Huddy, Norman Walter (Monterey, California. U.S. Naval Postgraduate School, 1966-10);A discussion of the nature of speech is presented, followed by a review of speech processing to date, with emphasis on the characteristics of speech which must be retained for intelligibility. Methods of measuring speech ...
Kelly, John David (Monterey, California. Naval Postgraduate School, 2007-03);Current mission driven systems, be they games or training simulations, are generally restricted to using a set of training missions that are hard coded into the system. This has the unfortunate effect of limiting the ...