[Corpora-List] Learning affix rules from wordlist

[Eric Atwell]

Tang,

My earlier posting could be what you are looking for!
- unsupervised learning of morphological analysers from corpus wordlists:

Date: Fri, 31 Mar 2006 12:15:17 +0100 (BST)
From: Eric Atwell <eric at comp.leeds.ac.uk>
To: Zhu Zhang <zhuzhang at U.Arizona.EDU>
Cc: corpora at uib.no
Subject: Re: [Corpora-List] Morphological analyzer?

The PASCAL MorphoChallenge contest results have just been published
http://www.cis.hut.fi/morphochallenge2005/results.shtml

- this includes descriptions (and accuracy) for a range of morphological
analysers, take your pick!  actually better scores was achieved by
combining system outputs in a majority-voting system (Combinatory Hybrid
Elementary
Analysis of Text, a carefully-chosen acronym :-)

These are unsupervised learning systems, which have the advantage of
being adaptable to other languages - the contestants had to test their
systems on Finnish and Turkish as well as English.

Eric Atwell, Leeds University

PS why not come to the PASCAL Challenge Workshop in Venice, April 10-12?


On Fri, 31 Mar 2006, Zhu Zhang wrote:

>
> Dear list,
>
> I'm looking for a good morphological analyzer for English that provides
> not only the base form of a word but also it's constituent morphemes
> (including prefixes and suffixes). Could you please offer any
> suggestions?
>
> Thanks!
>
> Zhu
>




On Mon, 10 Apr 2006, xuri tang wrote:

> Hi, listmembers.
>  Has anybody done any research on the automatic learning of English affix rules from a wordlist? I am trying to do that and am stuck there.
>  Many thanks.
>
>  Tang Xuri,
>  Dpt. Foreign Languages,
>  Wuhan University of Science and Engineering,
>  Wuhan, P.R. China
>
>
> ---------------------------------
> Ïë³ÉΪ·ëС¸Õ¡¢³Â¿­¸è¡¢ÕżÍÖÐÈý´óµ¼ÑݵÄÖ÷½ÇÂð£¿

-- 
Eric Atwell, Senior Lecturer, Language research group, School of Computing,
Faculty of Engineering, University of Leeds, LEEDS LS2 9JT, England
TEL: +44-113-3435430  FAX: +44-113-3435468  http://www.comp.leeds.ac.uk/eric