Re: [Corpora-List] Look for a lemma list

From: Xiaotian Guo (garlickfred@gmail.com)
Date: Wed Feb 21 2007 - 21:48:34 MET

  • Next message: Mikhail Kopotev: "[Corpora-List] Variant verbal government extraction"

    Hi, Fangzhong

    I encountered the same problem when I needed to compile a verb lemma list
    for a learner corpus study in my PhD. I am afraid you need to do some manual
    work to include in your ready-made lemma list what is needed such as both
    American and British spellings, if there is no better lemma list available.

    Yasumasa Someya's lemma list is not without problems. You need to check and
    correct some of the potential problems to cater for your own needs. One
    problem with Someya's lemma list is that verbs and nouns are mixed. If you
    need to sort this problem out, you might like to use the sorting function of
    MS Excel to distinguish nouns from verbs because the base form of a verb has
    more inflections than a singular noun.

    If you cannot get a better revised or edited lemma list, Someya's lemma list
    can still serve as a base for you to build on.

    Dr. Xiaotian Guo

    PhD in Corpus Linguistics (*looking for a job*)
    The Department of English
    The University of Birmingham
    Edgbaston, Birmingham, B15 2TT, UK

    On 2/21/07, fzsu <fzsu@comp.leeds.ac.uk> wrote:
    >
    > Dear all,
    >
    >
    >
    > Sorry to take your time.
    >
    >
    >
    > I am looking for an English lemma list, which can provide the
    > transformation between the basic form and the inflection form or the
    > derivation form.
    >
    > Here are some examples:
    >
    > abacus -> abacuses
    >
    > abandon -> abandons,abandoning,abandoned
    >
    > abase -> abases,abasing,abased
    >
    > abate -> abates,abating,abated
    >
    > abbess -> abbesses
    >
    > …………..
    >
    >
    >
    > I have downloaded a similar list complied by Yasumasa Someya, but apply
    > this list in my corpus, I can't get a satisfactory lemmatised cover rate for
    > some reasons.
    >
    > Now I hope to find some other lemma lists, and if they include both
    > American spelling and British spelling, that would be the best.
    >
    >
    >
    > If anyone has the lemma list resources, would you please sent them to me
    > or just give me a website link?
    >
    >
    >
    > Thank you.
    >
    >
    >
    > Fangzhong
    >
    >
    >



    This archive was generated by hypermail 2b29 : Wed Feb 21 2007 - 21:47:31 MET