Re: [Corpora-List] Chinese POS tagger and syntactic parser.

From: liuqun (liuqun@ict.ac.cn)
Date: Wed Jun 01 2005 - 04:56:14 MET DST

  • Next message: Menno van Zaanen: "[Corpora-List] Call for participation: IJCAI workshop on Grammatical Inference Applications"

    The Chinese segmentater and POS tagger (ICTCLAS) and Chinese parser (ICTPROP)
    was developed by our group --
    the NLP group in Institute of Computing Technlogy, Chinese Academy of Sciences.

    ICTCLAS is a full functional Chinese word segmentater and POS tagger.
    It got a good result in the first SIGHAN Chinese word segmentation
    bakeoff. An open source version for ICTCLAS is called freeICTCLAS.
    For source code and linux port for freeICTCLAS, please visit
    "Chinese NLP Platform" (http://www.nlp.org.cn).
    You should register an account using your real information before downloading
    the freeICTCLAS. The online test for ICTCLAS is:
        http://mtgroup.ict.ac.cn/~zhp/ICTCLAS.htm

    ICTPROP is a probabilistic Chinese parser, which is trained using
    Penn Chinese Treebank (ver1.0). Both label precision and recall
    of ICTPROP are about 77%.
    A free version of ICTPROP is also available in "Chinese NLP Platform".
    However, the free version of ICTPROP is just a prototype system,
    which was trained with a smaller treebank rather than Penn Chinese Treebank.
    The online test for full version ICTPROP is:
        http://mtgroup.ict.ac.cn/parserform.html

    All the above webpages are in Chinese, there is no English version currently.
    For more information of ICTCLAS and ICTPROP, please contact me.

    Liu Qun

    On Sun, 29 May 2005 19:18:08 +1000 (EST)
    Yuanyong Wang <wyy@cse.unsw.EDU.AU> wrote:

    >
    >
    >
    > Dear list memebers, I'm a research student at UNSW (university of
    > New South Wales, Australia) doing research on NLP, (WSD)word sense
    > disambiguation in particular. Recently, I'm attempting to utilize the
    > information provided by bilingual approaches (such as machine translation)
    > back on WSD in English. For that reason, I'm trying to set up the
    > environment for machine translation between English and Chinses. But I
    > found it quite cumbersome to set up such an environment under Linux,
    > should I just switch to Windows? I also tried a couple of Chinese POS
    > taggers and parsers, some are ok, but apparently I am expecting something
    > better. Could anyone kindly suggest me with some top Chinses POS taggers
    > and syntactic parsers? I'm also looking forward to exchanging ideas and
    > knowledge with anyone who's interested in similar topic. Thanks very much.
    >
    >
    >
    >
    >
    > Regards
    > Robin
    >
    >
    >

    ----
    LIU Qun (http://mtgroup.ict.ac.cn/~liuqun)
    



    This archive was generated by hypermail 2b29 : Wed Jun 01 2005 - 05:18:18 MET DST