2012 · 79 citations · 33 references
Open access
Language StudiesComputer ScienceFrenchComputational LinguisticsNatural Language ProcessingSyntaxGrammarN-gram AnalysisParsingSyntactic AnalysisSyntactic ParsingSyntax ParsingDiscontinuous SyntaxIdentificationMultiword Expression ProcessingN-gram StatisticsSurface Feature StatisticsTree Grammars
Multiword expressions (MWE), a known nuisance for both linguistics and NLP, blur the lines between syntax and semantics. Previous work on MWE identification has relied primarily on surface statistics, which perform poorly for longer MWEs and cannot model discontinuous expressions. To address these problems, we show that even the simplest parsing models can effectively identify MWEs of arbitrary length, and that Tree Substitution Grammars achieve the best results. Our experiments show a 36.4 % F1 absolute improvement for French over an n-gram surface statistics baseline, currently the predominant method for MWE identification. Our models are useful for several NLP tasks in which MWE pre-grouping has improved accuracy. 1
33
Mark Hall, Eibe Frank, Geoffrey Holmes et al. · ACM SIGKDD Explorations Newsletter · 2009 · 17.8K citations
Accurate unlexicalized parsing
Dan Klein, Christopher D. Manning · 2003 · 3.1K citations · Full text
Language Studies, Computer Science, Computational Linguistics +13
Learning accurate, compact, and interpretable tree annotation
Slav Petrov, Leon Barrett, Romain Thibaux et al. · 2006 · 812 citations · Full text
Retrieving collocations from text: Xtract
Frank Smadja · 1993 · 800 citations