From lingua at geez.org Sat Jul 8 12:30:12 2006 From: lingua at geez.org (Daniel Yacob) Date: Sat Jul 8 12:30:28 2006 Subject: [am-nlp] ICES-XVI & The CRL Say Corpus Message-ID: Greetings All, The 16th International Conference of Ethiopian Studies was announced this week: http://www.svt.ntnu.no/ices2007/ This is the longest running conference of Ethiopian studies, held approximately every 3 years with every 3rd conference hosted in Addis Ababa. I've attended only the previous one held in Hamburg and found that it was an excellent gathering of people who study every aspect of Ethiopian topics -12 tracks worth! NLP topics were presented at the Hamburg conference, so please do not hesitate to submit abstracts. Imagine if NLP could gain its own track! We could be just 16 papers away from such a goal. I have been late to point out the growing corpus of parallel text (Amharic-English and English-Amharic) being developed under the New Mexico State University's "Say" project which is producing quite a bit of publically available lexical resources: http://crl.nmsu.edu/say/ Their goal is to produce 100,000 words of sentended aligned English-Amharic translated text (already surpassed) and 300,000 words of Amharic-English (over 1/3 complete) based on topical news articles (click on "Resources" then "Parallel-text sentence aligned"). A freely available (copyright unencombered) Amharic-English lexicon of some 10,000 words will also be developed by the project. cheers, /Daniel