A Local Grammar of French determiners for deep syntactic parsing

2000

We present the Modified French Treebank (MFT), a completely revamped French Treebank, derived from the Paris 7 Tree- bank (P7T), which is cleaner, more co- herent, has several transformed structures, and introduces new linguistic analyses. To determine the effect of these changes, we investigate how the MFT fares in statistical parsing. Probabilistic parsers trained on the MFT training set (currently

2009

Recent years have seen considerable success in the generation of automatically obtained wide-coverage deep grammars for natural language processing, given reliable and large CFG-like treebanks. For research within Lexical Functional Grammar framework, these deep grammars are typically based on an extended PCFG parsing scheme from which dependencies are extracted. However, increasing success in statistical dependency parsing suggests that such deep grammar approaches to statistical parsing could be streamlined. We explore this novel approach to deep grammar parsing within the framework of LFG in this paper, for French, showing that best results (an f-score of 69.46) for the established integrated architecture may be obtained for French.

Proceedings of the …, 2004

This paper presents EASY (Evaluation of Analyzers of SYntax), an ongoing evaluation campaign of syntactic parsing of French, a subproject of EVALDA in the French TECHNOLANGUE program. After presenting the elaboration of the annotation formalism, we describe the corpus building steps, the annotation tools, the evaluation measures and finally, plans to produce a validated large linguistic resource, syntactically annotated.

Computational Linguistics, 2008

A number of researchers have recently conducted experiments comparing "deep" hand-crafted wide-coverage with "shallow" treebank-and machine-learning-based parsers at the level of dependencies, using simple and automatic methods to convert tree output generated by the shallow parsers into dependencies. In this article, we revisit such experiments, this time using sophisticated automatic LFG f-structure annotation methodologies with surprising results. We compare various PCFG and history-based parsers to find a baseline parsing system that fits best into our automatic dependency structure annotation technique. This combined system of syntactic parser and dependency structure annotation is compared to two hand-crafted, deep constraint-based parsers, RASP and XLE. We evaluate using dependency-based gold standards Computational Linguistics Volume 34, Number 1 and use the Approximate Randomization Test to test the statistical significance of the results. Our experiments show that machine-learning-based shallow grammars augmented with sophisticated automatic dependency annotation technology outperform hand-crafted, deep, widecoverage constraint grammars. Currently our best system achieves an f-score of 82.73% against the PARC 700 Dependency Bank, a statistically significant improvement of 2.18% over the most recent results of 80.55% for the hand-crafted LFG grammar and XLE parsing system and an f-score of 80.23% against the CBS 500 Dependency Bank, a statistically significant 3.66% improvement over the 76.57% achieved by the hand-crafted RASP grammar and parsing system.

2010

We first describe the automatic conversion of the French Treebank (Abeillé and , a constituency treebank, into typed projective dependency trees. In order to evaluate the overall quality of the resulting dependency treebank, and to quantify the cases where the projectivity constraint leads to wrong dependencies, we compare a subset of the converted treebank to manually validated dependency trees. We then compare the performance of two treebank-trained parsers that output typed dependency parses. The first parser is the MST parser , which we directly train on dependency trees. The second parser is a combination of the Berkeley parser (Petrov et al., 2006) and a functional role labeler: trained on the original constituency treebank, the Berkeley parser first outputs constituency trees, which are then labeled with functional roles, and then converted into dependency trees. We found that used in combination with a high-accuracy French POS tagger, the MST parser performs a little better for unlabeled dependencies (UAS=90.3% versus 89.6%), and better for labeled dependencies (LAS=87.6% versus 85.6%).

2011

In order to obtain a fine-grained evaluation of parser accuracy over naturally occurring text, we study 100 examples each of ten reasonably frequent linguistic phenomena, randomly selected from a parsed version of the English Wikipedia. We construct a corresponding set of gold-standard target dependencies for these 1000 sentences, operationalize mappings to these targets from seven state-of-theart parsers, and evaluate the parsers against this data to measure their level of success in identifying these dependencies.

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

The development of robust "deep" linguistic parsers is known to be a difficult task. Few such systems can claim to satisfy the needs of large-scale NLP applications in terms of robustness, efficiency, granularity or precision. Adapting such systems to more than one language makes the task even more challenging. This paper describes some of the properties of Fips, a multilingual parsing system that has been for a number of years (and still is) under development at LATL. Based on Chomsky's generative grammar for its grammatical aspects, and on objectoriented (OO) sofware engineering techniques for its implementation, Fips is designed to efficiently parse the four Swiss "national" languages (German, French, Italian and English) to which we also added Spanish and (more recently) Greek.

Proceedings of the EACL 2009 Workshop on Computational Linguistic Aspects of Grammatical Inference - CLAGI '09, 2009

This paper reports results on grammatical induction for French. We investigate how to best train a parser on the French Treebank (Abeillé et al., 2003), viewing the task as a trade-off between generalizability and interpretability. We compare, for French, a supervised lexicalized parsing algorithm with a semi-supervised unlexicalized algorithm (Petrov et al., 2006) along the lines of (Crabbé and Candito, 2008). We report the best results known to us on French statistical parsing, that we obtained with the semi-supervised learning algorithm. The reported experiments can give insights for the task of grammatical learning for a morphologically-rich language, with a relatively limited amount of training data, annotated with a rather flat structure.