A system for reference resolution in the context of the multilingual environment of Machine Translation is proposed, and a description of the first stage of implementation described. We argue that a semantics-based approach is more language-independent than a syntax-based, and show how WordNet functions provide a basis for resolution of pronouns and anaphoric nouns. The focus of the inital stage is design and treatment of third person pronouns and of speaker recognition. The system has been integrated with the English Slot Grammar Parser, so that parse structures show reference relations.
By: Arendse Bernth
Published in: RC22627 in 2002
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .