| | |
Summary: Building a Sense-Distinguished Multilingual Lexicon
from Monolingual Corpora and Bilingual Lexicons
Marcus Sammer and Stephen Soderland
Turing Center
Dept. of Computer Science and Engineering
University of Washington, Seattle, WA 98195 USA
{sammer, soderlan} @cs.washington.edu
Abstract
Both lexical translation and knowledge-based translation
systems require sense-distinguished translation lexicons,
yet such lexicons are expensive to create manually.
However, the abundance of untagged monolingual
corpora and the availability of bilingual, machine-
readable dictionaries (MRDs) suggest an opportunity.
Our PanLexicon system takes advantage of these
resources to automatically construct a sense-
distinguished multilingual lexicon. The challenge for
PanLexicon is that free, bilingual MRDs do not make
sense distinctions, and often have spotty coverage.
PanLexicon uses word contexts from monolingual
|
