John Carroll

5 paper cards in Mova's library · 1987–2004

John Carroll wrote 5 of the papers Mova reads, in 1987–2004, most of them on Word sense disambiguation; often with Diana McCarthy, Guido Minnen, Julie Weeds.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Finding Predominant Word Senses in Untagged Text (2004)
The most-frequent (predominant) sense is a strong baseline for word sense disambiguation, but it normally needs a hand-tagged corpus such as SemCor, which is small (about 250,000 words) and fixed in genre.
Automatic Identification of Infrequent Word Senses (2004)
The paper ranks the senses of a word without any sense-tagged data, using a thesaurus built from raw text (a BNC thesaurus of distributional neighbours) and WordNet similarity.
Robust, applied morphological generation (2000)
Natural language generation systems often need a separate component that turns a lemma, a part of speech and an inflection type into a word form.
Corpus Annotation for Parser Evaluation (1999)
Bracket-based parser scores (PARSEVAL) are hard to compare across grammars, because the bracketing of a treebank and the output of a parser differ in ways that are not errors.
The Derivation of a Grammatically Indexed Lexicon from the Longman Dictionary of Contemporary English (1987)
The authors build a large lexicon with grammatical feature entries for a morphological and syntactic analyser (GPSG-based, from the Alvey toolkit project) by deriving it from the machine-readable Longman Dictionary of Contemporary English (LDOCE).