Learn More
In learning their native language, children develop a remarkable set of capabilities. They acquire knowledge and skills that enable them to produce and comprehend an indeenite number of novel utterances, and to make quite subtle judgments about certain of their properties. The major goal of psycholinguistic research is to devise an explanatory account of(More)
We present a stochastic parsing system consisting of a Lexical-Functional Grammar (LFG), a constraint-based parser and a stochastic disambiguation model. We report on the results of applying this system to parsing the UPenn Wall Street Journal (WSJ) treebank. The model combines full and partial parsing techniques to reach full grammar coverage on unseen(More)
This paper reports some experiments that compare the accuracy and performance of two stochastic parsing systems. The currently popular Collins parser is a shallow parser whose output contains more detailed semantically-relevant information than other such parsers. The XLE parser is a deep-parsing system that couples a Lexical Functional Grammar to a(More)
Many modern grammatical formalisms divide the task of linguistic specification into a context-free component of phrasal constraints and a separate component of attribute-value or functional constraints. Conventional methods for recognizing the strings of a language also divide into two parts so that they can exploit the different computational properties of(More)
1 We are indebted to Milward (1994) for provoking and providing a starting point for this renewed research on coordination. Many of these ideas were discussed at various meetings and in email discussions and we thank the many participants: Caroline Brun, Max Copperman, Mary Dalrymple, Marc Dymetman, John Fry, Ron Kaplan, Lauri Karttunen, Martin Kay, Paula(More)
We present an approach to statistical machine translation that combines ideas from phrase-based SMT and traditional grammar-based MT. Our system incorporates the concept of multi-word translation units into transfer of dependency structure snippets, and models and trains statistical components according to state-of-the-art SMT systems. Compliant with(More)
When lingusitically motivated grammars are implemented on a larger scale, and applied to real-life corpora, keeping track of ambiguity sources becomes a difficult task. Yet it is of great importance, since unintended ambiguities arising from underrestricted rules or interactions have to be distinguished from linguistically warranted ambiguities. In this(More)