John Nerbonne, Duco Dokter and Petra Smit (1998): 'Morphological processing and computer-assisted language learning' (Computer Assisted Language Learning 11(5) pp. 543-559).
MOTIVATION: CALL systems do not generally make use of NLP technology - they limit themselves to putting self-study courses into electronic form, and hence use hand-coded/hard-wired linguistic knowledge. However, there are many CALL subtasks which should benefit from state-of-the-art (almost 'error-free') morphological or phonological processing, i.e. for use as 'support tools' in analysis of 'authentic materials', and acquisition of vocabulary.
SYSTEM DESCRIPTION: GLOSSER is a program which allows Dutch learners of French to import French texts, select individual words, and get information about these words. The main frame is a read-only text display for the source text. There are three minor frames giving information about the selected word: (a) dictionary definition (for the underlying lexeme) from the Van Dale French-Dutch dictionary; (b) (disambiguated) POS and morphological analysis; and (c) other example sentences using forms of the underlying lexeme (including some from bilingual corpora). Users can add NOTES to each selected word, to avoid multiple look-ups. The morphological analysis/POS disambiguation/lexeme identification is done using the state-of-the-art LOCOLEX software (from the Rank Xerox Research Centre).
There is a simple evaluation of the system (from the perspective of lexical coverage and accuracy). There was also a small user study with 22 students, comparing use of GLOSSER with traditional physical dictionary lookup in a traditional text comprehension task, with generally positive results.
COMMENT: The authors point out the problem of identifying 'multi-word lexemes' in source text as being worthy of future work. This is a big question. Integration with some kind of personal vocabulary database (flashcard generator?) would be a good idea. Can this idea be extended for spoken language files or videos?
The GLOSSER homepage.
No comments:
Post a Comment