Downloads & Free Reading Options - Results

This paper presents a grammar formalism designed for use in data-oriented approaches to language processing. The formalism is best described as a right-linear indexed grammar extended in linguistically interesting ways. The paper goes on to investigate how a corpus pre-parsed with this formalism may be processed to provide a probabilistic language model for use in the parsing of fresh texts.

This paper presents a new view of Explanation-Based Learning (EBL) of natural language parsing. Rather than employing EBL for specializing parsers by inferring new ones, this paper suggests employing EBL for learning how to reduce ambiguity only partially. The present method consists of an EBL algorithm for learning partial-parsers, and a parsing algorithm which combines partial-parsers with existing ``full-parsers". The learned partial-parsers, implementable as Cascades of Finite State Transducers (CFSTs), recognize and combine constituents efficiently, prohibiting spurious overgeneration. The parsing algorithm combines a learned partial-parser with a given full-parser such that the role of the full-parser is limited to combining the constituents, recognized by the partial-parser, and to recognizing unrecognized portions of the input sentence. Besides the reduction of the parse-space prior to disambiguation, the present method provides a way for refining existing disambiguation models that learn stochastic grammars from tree-banks. We exhibit encouraging empirical results using a pilot implementation: parse-space is reduced substantially with minimal loss of coverage. The speedup gain for disambiguation models is exemplified by experiments with the DOP model.

Data-Oriented Parsing (dop) ranks among the best parsing schemes, pairing state-of-the art parsing accuracy to the psycholinguistic insight that larger chunks of syntactic structures are relevant grammatical and probabilistic units. Parsing with the dop-model, however, seems to involve a lot of CPU cycles and a considerable amount of double work, brought on by the concept of multiple derivations, which is necessary for probabilistic processing, but which is not convincingly related to a proper linguistic backbone. It is however possible to re-interpret the dop-model as a pattern-matching model, which tries to maximize the size of the substructures that construct the parse, rather than the probability of the parse. By emphasizing this memory-based aspect of the dop-model, it is possible to do away with multiple derivations, opening up possibilities for efficient Viterbi-style optimizations, while still retaining acceptable parsing accuracy through enhanced context-sensitivity.

In this paper I present ongoing work on the data-oriented parsing (DOP) model. In previous work, DOP was tested on a cleaned-up set of analyzed part-of-speech strings from the Penn Treebank, achieving excellent test results. This left, however, two important questions unanswered: (1) how does DOP perform if tested on unedited data, and (2) how can DOP be used for parsing word strings that contain unknown words? This paper addresses these questions. We show that parse results on unedited data are worse than on cleaned-up data, although very competitive if compared to other models. As to the parsing of word strings, we show that the hardness of the problem does not so much depend on unknown words, but on previously unseen lexical categories of known words. We give a novel method for parsing these words by estimating the probabilities of unknown subtrees. The method is of general interest since it shows that good performance can be obtained without the use of a part-of-speech tagger. To the best of our knowledge, our method outperforms other statistical parsers tested on Penn Treebank word strings.