Most state-of-the-art wide-coverage parsers are trained on newspaper text and suffer a loss of accuracy in other domains, making parser adaptation a ...
Most state-of-the-art wide-coverage parsers are trained on newspaper text and suffer a loss of accuracy in other domains, making parser adaptation a ...
In this paper we demonstrate that a CCG parser can be adapted to two new domains, biomedical text and questions for a QA system, by using manually-annotated ...
Adapting a Lexicalized-Grammar Parser to Contrasting Domains
www.semanticscholar.org › paper › Ada...
It is demonstrated that a CCG parser can be adapted to two new domains, biomedical text and questions for a QA system, by using manually-annotated training ...
Adapting a Lexicalized-Grammar Parser to Contrasting Domains.
www.researchgate.net › ... › Newspapers
We find that retraining at the lexical category level yields a larger performance increase for questions than for biomedical text and analyze the two datasets ...
Bibliographic details on Adapting a Lexicalized-Grammar Parser to Contrasting Domains.
We have presented a method for adapting a lexicalized-grammar parser to the biomedical domain which leverages the parser's existing wide-coverage grammar ...
Feb 7, 2015 · Self-training is a technique used to adapt a lexicalized parser to a new target domain. ... Porting a lexicalized-grammar parser to the biomedical ...
Our objective was to adapt an existing general English parser for the clinical text of operative reports via lexicon augmentation, statistics adjusting, and ...
Rimell and Clark (2008), Yes, 81.5, Adapting a Lexicalized-Grammar Parser to Contrasting Domains ; Xu et al. (2015), No, 77.74, CCG Supertagging with a Recurrent ...