An important aspect of semantic analysis of a discourse is the identification and resolution of implicit arguments of verbs, nouns etc. Making implicit arguments explicit enables extraction of relations that would otherwise be hidden to an application of the semantic analysis such as question-answering. We describe how the discourse understanding system Euphoria uses parsing, syntactic rules, semantic rules, and coreference resolution to determine implicit arguments. The semantic representation for a discourse consists of a set of entity-oriented logical forms indexed by the entities of the discourse, enabling efficient access to everything that is said about each discourse entity. Empirical evaluation of Euphoria shows significant improvements in resolving implicit arguments as compared to sentence-based processing.
By: Arendse Bernth
Published in: RC24046 in 2006
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 .