Foundations of Statistical Natural Language Processing
Christopher D. Manning and Hinrich Schütze
Chapter 7: Word Sense Disambiguation
Links referred to in the text
Home page of the
Senseval project
, a large-scale evaluation of word sense disambiguation algorithms.
An old (1911) version of Roget's thesaurus can be downloaded from
Project Gutenberg
.
Romanseval
Corpora for the evaluation of Word Sense Disambiguation are available from the
Linguistic Data Consortium (search for "sense")
DSO Corpus of Sense-Tagged English Nouns and Verbs
SEMCOR: Semantic Concordance
Other links
Papers on inter-annotator agreement
Christopher Manning and Hinrich Schütze --