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 data. The treebank annotations are used to provide partially labeled data for discriminative statistical estimation using exponential models. Disambiguation performance is evaluated by measuring matches of predicate-argument relations on two distinct test sets. On a gold standard of manually annotated f-structures for a subset of the WSJ treebank, this evaluation reaches 79% F-score. An evaluation on a gold standard of dependency relations for Brown corpus data achieves 76% F-score.
Ahstract: This paper outlines a theory of constituent coordination For l,exicaI-Funetional Grammar. On this theory LFG's flat, unstructured nets are used as the functional representation of coordinate constructions, l"unction application is extended to sets by treating a set tbrmally am the generalization of its Functional clmnents. This causes properties attributed externally to a coordinate structure to be uniformly distributed across its elements, without requiring additional grammatical specifications.
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 stateof-the-art SMT systems. Compliant with classical transfer-based MT, target dependency structure snippets are input to a grammar-based generator. An experimental evaluation shows that the incorporation of a grammar-based generator into an SMT framework provides improved grammaticality while achieving state-of-the-art quality on in-coverage examples, suggesting a possible hybrid framework.
We report on the XLE parser and grammar development platform (Maxwell and Kaplan, 1993) and describe how a basic Lexical Functional Grammar for English has been adapted to two different corpora (newspaper text and copier repair tips).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.