Robust and Statistical Parsing in GF

TitleRobust and Statistical Parsing in GF
Publication TypeSlide Presentation
AuthorsAngelov, K
PublisherThe MOLTO Consortium
Place PublishedBarcelona, Spain
Year of Publication2013
Date Published05/2013
Publication LanguageEnglish

In this talk we review the state of turning Grammatical Framework to a hybride combining lingustic knowledge with statistical evidence. Our statistical parser already outperforms the existing state of the art parsers for related formalisms. For one and the same grammar we show a speed-up of up to two orders of magnitude without sacrificing the quality. In addition the grammarians can still use the high-level GF language for developing their grammars. In MOLTO we have promised a scale of hundreds of lemmas while in this experiment we have shown that we can scale to thousands. On top of the new hybride we have built an experimental robust translator which is based entirely on GF.

KeywordsFinal Project Meeting - Barcelona 2013
Type of WorkPresentation
stat-parsing.pdf366.71 KB