A best-first probabilistic shift-reduce parser (original) (raw)

A classifier-based parser with linear run-time complexity

Proceedings of the Ninth International Workshop …, 2005

We present a classifier-based parser that produces constituent trees in linear time. The parser uses a basic bottom-up shiftreduce algorithm, but employs a classifier to determine parser actions instead of a grammar. This can be seen as an extension of the deterministic dependency parser of to full constituent parsing. We show that, with an appropriate feature set used in classification, a very simple one-path greedy parser can perform at the same level of accuracy as more complex parsers. We evaluate our parser on section 23 of the WSJ section of the Penn Treebank, and obtain precision and recall of 87.54% and 87.61%, respectively.

Improving shift-reduce constituency parsing with large-scale unlabeled data

Natural Language Engineering, 2013

Shift-reduce parsing has been studied extensively for diverse grammars due to the simplicity and running efficiency. However, in the field of constituency parsing, shift-reduce parsers lag behind state-of-the-art parsers. In this paper we propose a semi-supervised approach for advancing shift-reduce constituency parsing. First, we apply the uptraining approach (Petrov, S. et al. 2010. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), Cambridge, MA, USA, pp. 705–713) to improve part-of-speech taggers to provide better part-of-speech tags to subsequent shift-reduce parsers. Second, we enhance shift-reduce parsing models with novel features that are defined on lexical dependency information. Both stages depend on the use of large-scale unlabeled data. Experimental results show that the approach achieves overall improvements of 1.5 percent and 2.1 percent on English and Chinese data respectively. Moreover, the final parsing accuracies rea...

Fast and Accurate Shift-Reduce Constituent Parsing

Shift-reduce dependency parsers give comparable accuracies to their chart-based counterparts, yet the best shift-reduce constituent parsers still lag behind the state-of-the-art. One important reason is the existence of unary nodes in phrase structure trees, which leads to different numbers of shift-reduce actions between different outputs for the same input. This turns out to have a large empirical impact on the framework of global training and beam search. We propose a simple yet effective extension to the shift-reduce process, which eliminates size differences between action sequences in beam-search. Our parser gives comparable accuracies to the state-of-the-art chart parsers. With linear run-time complexity, our parser is over an order of magnitude faster than the fastest chart parser.

Probabilistic GLR parsing: A new formalization and its impact on parsing performance

Journal of Natural …, 1998

This paper presents a new formalization of probabilistic GLR (PGLR) language modeling for statistical parsing. Our model inherits its essential features from Briscoe and Carroll's generalized probabilistic LR model , which takes context of parse derivation into account by assigning a probability to each LR parsing action according to its left and right context. Briscoe and Carroll's model, however, has a drawback in that it is not formalized in any probabilistically well-founded way, which may degrade its parsing performance. Our formulation overcomes this drawback with a few significant refinements, while maintaining all the advantages of Briscoe and Carroll's modeling. In this paper, we discuss the formal and qualitative aspects of our PGLR model, illustrating the qualitative differences between Briscoe and Carroll's model and our model, and their expected impact on parsing performance.

Parse Selection on the Redwoods Corpus: 3rd Growth Results

2003

This report details experimental results of using stochastic disambiguation models for parsing sentences from the Redwoods treebank (Oepen et al., 2002). The goals of this paper are twofold: (i) to report accuracy results on the more highly ambiguous latest version of the treebank, as compared to already published results achieved by the same stochastic models on a previous version of the corpus, and (ii) to present some newly developed models using features from the HPSG signs, as well as the MRS dependency graphs.

Adapting a WSJ-trained parser to grammatically noisy text

Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08, 2008

We present a robust parser which is trained on a treebank of ungrammatical sentences. The treebank is created automatically by modifying Penn treebank sentences so that they contain one or more syntactic errors. We evaluate an existing Penn-treebank-trained parser on the ungrammatical treebank to see how it reacts to noise in the form of grammatical errors. We re-train this parser on the training section of the ungrammatical treebank, leading to an significantly improved performance on the ungrammatical test sets. We show how a classifier can be used to prevent performance degradation on the original grammatical data.

Pruning the search space of a hand-crafted parsing system with a probabilistic parser

Proceedings of the Workshop on Deep Linguistic Processing - DeepLP '07, 2007

The demand for deep linguistic analysis for huge volumes of data means that it is increasingly important that the time taken to parse such data is minimized. In the XLE parsing model which is a hand-crafted, unification-based parsing system, most of the time is spent on unification, searching for valid f-structures (dependency attributevalue matrices) within the space of the many valid c-structures (phrase structure trees). We carried out an experiment to determine whether pruning the search space at an earlier stage of the parsing process results in an improvement in the overall time taken to parse, while maintaining the quality of the f-structures produced. We retrained a stateof-the-art probabilistic parser and used it to pre-bracket input to the XLE, constraining the valid c-structure space for each sentence. We evaluated against the PARC 700 Dependency Bank and show that it is possible to decrease the time taken to parse by ∼18% while maintaining accuracy.

Building a large annotated corpus of English: the penn treebank

Computational Linguistics, 1994

There is a growing consensus that significant, rapid progress can be made in both text understanding and spoken language understanding by investigating those phenomena that occur most centrally in naturally occurring unconstrained materials and by attempting to automatically extract information about language from very large corpora. Such corpora are beginning to serve as important research tools for investigators in natural language processing, speech recognition, and integrated spoken language systems, as well as in theoretical linguistics. Annotated corpora promise to be valuable for enterprises as diverse as the automatic construction of statistical models for the grammar of the written and the colloquial spoken language, the development of explicit formal theories of the differing grammars of writing and speech, the investigation of prosodic phenomena in speech, and the evaluation and comparison of the adequacy of parsing models.

Head-Driven Statistical Models for Natural Language Parsing

Computational Linguistics, 2003

This article describes three statistical models for natural language parsing. The models extend methods from probabilistic context-free grammars to lexicalized grammars, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree. Independence assumptions then lead to parameters that encode the X-bar schema, subcategorization, ordering of complements, placement of adjuncts, bigram lexical dependencies, wh-movement, and preferences for close attachment. All of these preferences are expressed by probabilities conditioned on lexical heads. The models are evaluated on the Penn Wall Street Journal Treebank, showing that their accuracy is competitive with other models in the literature. To gain a better understanding of the models, we also give results on different constituent types, as well as a breakdown of precision/recall results in recovering various types of dependencies. We analyze various characteristics of the models through experiments on parsing accuracy, by collecting frequencies of various structures in the treebank, and through linguistically motivated examples. Finally, we compare the models to others that have been applied to parsing the treebank, aiming to give some explanation of the difference in performance of the various models.