Göm menyn
Files: Description Format
Fulltext PDF (requires Acrobat Reader)
Fulltext part 1 PostScript (requires a PostScript Reader)
  Fulltext part 2 PostScript (requires a PostScript Reader)
Authors: Mark Seligman, Jan Alexandersson, and Kristiina Jokinen
Article title: Tracking Morphological and Semantic Co-occurrences in Spontaneous Dialogues
Publ. type: Article
Volume: 4
Article No: 31
Language: English
Abstract [en]: In the processing of spontaneous language, information concerning discourse-level co-occurrences of words or morphemes - relatively long-term predictions on the scale of several utterances - may help to reduce perplexity in speech recognition, facilitate lexical disambiguation, and contribute to topic tracking. This working paper describes a new set of facilities for tracking lexical co-occurrences. The major innovation is the use of semantic smoothing: we track co-occurrences of semantic tokens associated with words or morphs in addition to co-occurrences of the words or morphs themselves. Such smoothing offers an approach to the problem of data sparseness: it is possible to retrieve reasonable semantically-mediated associations for morphs not in the training corpus. We report on preliminary experiments with a corpus of morphologically-tagged transcripts of 16 spontaneous Japanese dialogues concerning direction-finding and hotel arrangements. We close with discussion of lexical disambiguation and topic tracking as they relate to co-occurrence networks.
Publisher: Linköping University Electronic Press
Year: 1999
Available: 1999-12-30
No. of pages: 9
Series: Linköping Electronic Articles in Computer and Information Science
ISSN: 1401-9841

Responsible for this page: Peter Berkesand
Last updated: 2017-02-21