Statistical Parsing with Context-Free Filtering Grammar Michael Demko Master of Science Graduate Department of Computer Science University of Toronto 2007 Statistical parsers that simultaneously generate both phrase-structure and lexical dependency trees have been limited in two important ways: the detection of non-projective dependencies has not been integrated with other parsing decisions, or...

Linearization-based HPSG theories are widely used for analyzing languages with relatively free constituent order. This paper introduces the Generalized ID/LP (GIDLP) grammar format, which supports a direct encoding of such theories, and discusses key aspects of a parser that makes use of the dominance, precedence, and linearization domain information explicitly encoded in this grammar format. W...

This paper presents a fundamental algorithm for parsing natural language sentences into dependency trees. Unlike phrase-structure (constituency) parsers, this algorithm operates one word at a time, attaching each word as soon as it can be attached, corresponding to properties claimed for the parser in the human brain. Like phrasestructure parsing, its worst-case complexity is O(n), but in human...

The paper outlines a hybrid architecture for a partial parser based on regular grammars over XML documents. The parser is used to support the annotation process in the BulTreeBank project. Thus the parser annotates only the ‘sure’ cases. To maximize the number of the analyzed phrases the parser applies a set of grammars in a dynamic fashion. Each grammar determines not only the constituent stru...

We propose an improved, bottom-up method for converting CCG derivations into PTB-style phrase structure trees. In contrast with past work (Clark and Curran, 2009), which used simple transductions on category pairs, our approach uses richer transductions attached to single categories. Our conversion preserves more sentences under round-trip conversion (51.1% vs. 39.6%) and is more robust. In par...

Corpora of phrase-structure-annotated text, or treebanks, are useful for supervised training of statistical models for natural language processing, as well as for corpus linguistics. Their primary drawback, however, is that they are very time-consuming to produce. To alleviate this problem, the standard approach is to make two passes over the text: first, parse the text automatically, then corr...

1 Efficient natural language generation has been successfully demonstrated using highly compiled knowledge about speech acts and their related social actions. A design and prototype implementation of a parser which utilizes this same pragmatic knowledge to efficiently guide parsing is presented. Such guidance is shown to prune the search space and thus avoid needless processing of pragmatically...

In this paper we explore the idea of using verb valency information to improve verb phrase extraction from historical text. As a case study, we perform experiments on Early Modern Swedish data, but the approach could easily be transferred to other languages and/or time periods as well. We show that by using verb valency information in a post-processing step to the verb phrase extraction system,...

We descrlbe a general parsing m e t h o d for systemic grammars. Systemic grammars contain a paradigmatic analysis of language in addition to structural information, so a parser must assign a set o f grammatical features and functions to each constituent in addition to producing a constituent structure. Our method constructs a parser by compiling systemic grammars into the notation of Functiona...

Appositions are grammatical constructs in which two noun phrases are placed side-by-side, one modifying the other. Detecting them in speech can help extract semantic information useful, for instance, for co-reference resolution and question answering. We compare and combine three approaches: wordlevel and phrase-level classifiers, and a syntactic parser trained to generate appositions. On refer...