Training of dependency parsers

Dependency parsing, which is the task of automatically doing syntactic analysis and defining the binary dependencies between words in a sentence, has gained much attention from researchers in recent years. Besides that, to build effective and robust dependency parsers, we also need a large number of annotated treebanks to train the models. However, constructing such treebanks is complicated and requires considerable human effort.

8p visherylsandberg 18-05-2022 11 2   Download

Data-driven systems for natural language processing have the advantage that they can easily be ported to any language or domain for which appropriate training data can be found. However, many data-driven systems require careful tuning in order to achieve optimal performance, which may require specialized knowledge of the system. We present MaltOptimizer, a tool developed to facilitate optimization of parsers developed using MaltParser, a data-driven dependency parser generator.

5p bunthai_1 06-05-2013 46 3   Download

We present a model for sentence compression that uses a discriminative largemargin learning framework coupled with a novel feature set defined on compressed bigrams as well as deep syntactic representations provided by auxiliary dependency and phrase-structure parsers. The parsers are trained out-of-domain and contain a significant amount of noise. We argue that the discriminative nature of the learning algorithm allows the model to learn weights relative to any noise in the feature set to optimize compression accuracy directly.

8p bunthai_1 06-05-2013 37 1   Download

This paper presents results from the first statistical dependency parser for Turkish. Turkish is a free-constituent order language with complex agglutinative inflectional and derivational morphology and presents interesting challenges for statistical parsing, as in general, dependency relations are between “portions” of words – called inflectional groups. We have explored statistical models that use different representational units for parsing.

8p bunthai_1 06-05-2013 53 3   Download

The paper presents two approaches to partial parsing of German: a tagger trained on dependency tuples, and a cascaded finite-state parser (Abney, 1997). For the tagging approach, the effects of choosing different representations of dependency tuples are investigated. Performance of the finite-state parser is boosted by delaying syntactically unsolvable disambiguation problems via underspecification. Both approaches are evaluated on a 340,000-token corpus.

4p bunthai_1 06-05-2013 48 1   Download

This paper compares a number of generative probability models for a widecoverage Combinatory Categorial Grammar (CCG) parser. These models are trained and tested on a corpus obtained by translating the Penn Treebank trees into CCG normal-form derivations. According to an evaluation of unlabeled word-word dependencies, our best model achieves a performance of 89.9%, comparable to the figures given by Collins (1999) for a linguistically less expressive grammar. In contrast to Gildea (2001), we find a significant improvement from modeling wordword dependencies. ...

8p bunmoc_1 20-04-2013 35 2   Download

This paper describes a wide-coverage statistical parser that uses Combinatory Categorial Grammar (CCG) to derive dependency structures. The parser differs from most existing wide-coverage treebank parsers in capturing the long-range dependencies inherent in constructions such as coordination, extraction, raising and control, as well as the standard local predicate-argument dependencies. A set of dependency structures used for training and testing the parser is obtained from a treebank of CCG normal-form derivations, which have been derived (semi-) automatically from the Penn Treebank. ...

8p bunmoc_1 20-04-2013 44 2   Download

This paper reports the corpus-oriented development of a wide-coverage Japanese HPSG parser. We first created an HPSG treebank from the EDR corpus by using heuristic conversion rules, and then extracted lexical entries from the treebank. The grammar developed using this method attained wide coverage that could hardly be obtained by conventional manual development. We also trained a statistical parser for the grammar on the treebank, and evaluated the parser in terms of the accuracy of semantic-role identification and dependency analysis. ...

6p bunbo_1 17-04-2013 35 1   Download

Semantic role labeling is the process of annotating the predicate-argument structure in text with semantic labels. In this paper we present a state-of-the-art baseline semantic role labeling system based on Support Vector Machine classifiers. We show improvements on this system by: i) adding new features including features extracted from dependency parses, ii) performing feature selection and calibration and iii) combining parses obtained from semantic parsers trained using different syntactic views. ...

8p bunbo_1 17-04-2013 44 1   Download

We present an effective training algorithm for linearly-scored dependency parsers that implements online largemargin multi-class training (Crammer and Singer, 2003; Crammer et al., 2003) on top of efficient parsing techniques for dependency trees (Eisner, 1996). The trained parsers achieve a competitive dependency accuracy for both English and Czech with no language specific enhancements.

8p bunbo_1 17-04-2013 64 3   Download

Dependency structures do not have the information of phrase categories in phrase structure grammar. Thus, dependency parsing relies heavily on the lexical information of words. This paper discusses our investigation into the effectiveness of lexicalization in dependency parsing. Specifically, by restricting the degree of lexicalization in the training phase of a parser, we examine the change in the accuracy of dependency relations. Experimental results indicate that minimal or low lexicalization is sufficient for parsing accuracy. ...

4p hongvang_1 16-04-2013 29 1   Download

In this paper, we exploit non-local features as an estimate of long-distance dependencies to improve performance on the statistical spoken language understanding (SLU) problem. The statistical natural language parsers trained on text perform unreliably to encode non-local information on spoken language. An alternative method we propose is to use trigger pairs that are automatically extracted by a feature induction algorithm. We describe a light version of the inducer in which a simple modification is efficient and successful. ...

8p hongvang_1 16-04-2013 52 1   Download

We present a simple and effective semisupervised method for training dependency parsers. We focus on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated corpus. We demonstrate the effectiveness of the approach in a series of dependency parsing experiments on the Penn Treebank and Prague Dependency Treebank, and we show that the cluster-based features yield substantial gains in performance across a wide range of conditions. ...

9p hongphan_1 15-04-2013 38 1   Download

We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discriminative, convex, semi-supervised learning algorithm can be obtained that is applicable to large-scale problems. To demonstrate the benefits of this approach, we apply the technique to learning dependency parsers from combined labeled and unlabeled corpora.

9p hongphan_1 15-04-2013 38 2   Download

Broad-coverage annotated treebanks necessary to train parsers do not exist for many resource-poor languages. The wide availability of parallel text and accurate parsers in English has opened up the possibility of grammar induction through partial transfer across bitext. We consider generative and discriminative models for dependency grammar induction that use word-level alignments and a source language parser (English) to constrain the space of possible target trees.

9p hongphan_1 14-04-2013 58 2   Download

We consider a very simple, yet effective, approach to cross language adaptation of dependency parsers. We first remove lexical items from the treebanks and map part-of-speech tags into a common tagset. We then train a language model on tag sequences in otherwise unlabeled target data and rank labeled source data by perplexity per word of tag sequences from less similar to most similar to the target. We then train our target language parser on the most similar data points in the source labeled data. ...

5p hongdo_1 12-04-2013 45 3   Download

Compositional question answering begins by mapping questions to logical forms, but training a semantic parser to perform this mapping typically requires the costly annotation of the target logical forms. In this paper, we learn to map questions to answers via latent logical forms, which are induced automatically from question-answer pairs. In tackling this challenging learning problem, we introduce a new semantic representation which highlights a parallel between dependency syntax and efficient evaluation of logical forms. ...

10p hongdo_1 12-04-2013 55 4   Download

The definition of combinatory categorial grammar (CCG) in the literature varies quite a bit from author to author. However, the differences between the definitions are important in terms of the language classes of each CCG. We prove that a wide range of CCGs are strongly context-free, including the CCG of CCGbank and of the parser of Clark and Curran (2007). In light of these new results, we train the PCFG parser of Petrov and Klein (2007) on CCGbank and achieve state of the art results in supertagging accuracy, PARSEVAL measures and dependency accuracy. ...

10p hongdo_1 12-04-2013 36 1   Download

Treebanks are not large enough to reliably model precise lexical phenomena. This deficiency provokes attachment errors in the parsers trained on such data. We propose in this paper to compute lexical affinities, on large corpora, for specific lexico-syntactic configurations that are hard to disambiguate and introduce the new information in a parser. Experiments on the French Treebank showed a relative decrease of the error rate of 7.1% Labeled Accuracy Score yielding the best parsing results on this treebank....

9p nghetay_1 07-04-2013 49 1   Download