Lexical information is one of the most important source that can improve the accuracy of the syntactic disambigua-tion. This paper describes a Korean probabilistic parser that is based on the probabilities of phrase structure rules as well as the probabilities of collocational information between lexical items to resolve syntactic ambiguity. The proposed parser is shown by means of an extensive...

Structural ambiguity is one of the most difficult problems in natural language processing. Two disambiguation mechanisms for unrestricted text analysis are commonly used: lexical knowledge and context considerations. Our parsing method includes three different mechanisms to reveal syntactic structures and an additional voting module to obtain the most probable structures for a sentence. The dev...

We present a method for disambiguating syntactic subjects from syntactic objects (a frequent ambiguity) in German sentences taken from an English-German bitext. We exploit the fact that subject and object are usually easily determined in English. We show that a simple method disambiguates some subjectobject ambiguities in German, while making few errors. We view this procedure as the first step...

In this paper, we describe the design and integration of a three level cascaded non-deterministic finite state model of Turkish compounding into Turkish PAPPI, a comprehensive syntactic parser in the principles-andparameters(P&P) framework. Our approach is to handle compounding as an intermediate stage between morphological analysis and syntactic parsing. We discuss how the compounding machine ...

This paper tests whether listeners are able to use the prosodic characteristics of speech to differentiate between alternative interpretations of syntactically ambiguous stimuli. Most existing research has either employed off-line tasks or provided adequate syntactic information for the listener to recognise ambiguity but inadequate prosodic information to resolve it. In incorporating controls ...

The increasing use of large open-domain document sources is exacerbating the problem of ambiguity in named entities. This paper explores the use of a range of syntactic and semantic features in unsupervised clustering of documents that result from ad hoc queries containing names. From these experiments, we find that the use of robust syntactic and semantic features can significantly improve the...

A? algorithms enable efficient parsing within the context of large grammars and/or complex syntactic formalisms. Besides, it has been shown that promoting multiword expressions (MWEs) is a beneficial strategy in dealing with syntactic ambiguity. The state-of-the-art A? heuristic for promoting MWEs in tree-adjoining grammar (TAG) parsing has certain drawbacks: it is not monotonic and it composes...

We present an incremental Bayesian model for the unsupervised learning of syntactic categories from raw text. The model draws information from the distributional cues of words within an utterance, while explicitly bootstrapping its development on its own partiallylearned knowledge of syntactic categories. Testing our model on actual child-directed data, we demonstrate that it is robust to noise...