[Corpora-List] Sentence ambiguator/splitter

From: Staffan Hermansson (shend00@student.vxu.se)
Date: Tue Jan 27 2004 - 13:08:20 MET

  • Next message: Bruce L. Lambert, Ph.D.: "Re: [Corpora-List] What proportion of letter ngrams occur in English?"

    Hello everybody.

    I'm currently writing my master thesis with subject Sentence
    Disambiguation. I've been doing some basic research of other projects
    (see below), and read what have been written earlier on this mailing
    list. But I would appreciate any information regarding the subject, new
    or old.

    I'm aware that there are tools available. However, my main target
    language is Swedish and I'm not sure of how good their accuracy are at
    this. Thoughts anyone?

    Oh, and if someone could direct me to a online copy of Riley 1989, you
    would have my gratitude

    @inproceedings{ riley89,
    author = "Riley, Michael D.",
    title = "Some applications of tree-based modelling to speech and
    language indexing.",
    booktitle = "Proceedings of the DARPA Speech and Natural Language
    Workshop, Oxford",
    publisher = "Morgan Kaufmann",
    pages = "339-352",
    year = "1989",
    }

    Thanks, and please mind my English.
    //Staffan

    Sources for those who are interrested:
    J. Reynar and A. Ratnaparkhi,
    A Maximum Entropy Approach to Identifying Sentence Boundaries
    citeseer.nj.nec.com/article/reynar97maximum.html

    David D. Palmer and Marti A. Hearst,
    Adaptive Multilingual Sentence Boundary Disambiguation
    citeseer.nj.nec.com/palmer97adaptive.html

    Andrei Mikheev
    Tagging Sentence Boundaries,
    citeseer.nj.nec.com/mikheev00tagging.html 

    -- 
Staffan Hermansson <shend00@student.vxu.se>

    This archive was generated by hypermail 2b29 : Tue Jan 27 2004 - 15:20:47 MET