Treebank Conversion. Converting the NEGRA treebank to an LTAG grammar (original) (raw)

Treebank Conversion for LTAG Grammar Extraction

2001

We present a method for rule-based structure conversion of existing treebanks, which aims at the extraction of linguistically sound, corpus-based grammars. We apply this method to the NEGRA treebank (Skut et al., 1998) to derive an LTAG grammar of German. We describe the methodology and tools for structure conversion and LTAG extraction. The conversion and grammar extraction process imports linguistic knowledge and generalisations that are missing in the original treebank.

Extracting LTAG Grammars from a Spanish Treebank

Treebank grammars have been known to help in building robust, wide-coverage statistical parsers that also obtain state-of-art accuracies. In this work, we present a system that extracts LTAG grammars for Spanish from a constituency-based Spanish treebank. We evaluate the extracted grammar in terms of its size, its coverage on unseen data and the performance of a supertagger trained on it. The supertagger built using the MaxEnt framework achieves an error rate of 20.36% for a tagset containing 10,424 supertags.

Automated extraction of Tree-Adjoining Grammars from treebanks

Natural Language Engineering, 2005

There has been a contemporary surge of interest in the application of stochastic models of parsing. The use of tree-adjoining grammar (TAG) in this domain has been relatively limited due in part to the unavailability, until recently, of large-scale corpora hand-annotated with TAG structures. Our goals are to develop inexpensive means of generating such corpora and to demonstrate their applicability to stochastic modeling. We present a method for automatically extracting a linguistically plausible TAG from the Penn Treebank. Furthermore, we also introduce labor-inexpensive methods for inducing higher-level organization of TAGs. Empirically, we perform an evaluation of various automatically extracted TAGs and also demonstrate how our induced higher-level organization of TAGs can be used for smoothing stochastic TAG models.

Coping with problems in grammars automatically extracted from Treebanks

COLING-02 on Grammar engineering and evaluation -, 2002

We report in this paper on an experiment on automatic extraction of a Tree Adjoining Grammar from the WSJ corpus of the Penn Treebank. We use an automatic tool developed by (Xia, 2001) properly adapted to our particular need. Rather than addressing general aspects of the automatic extraction we focus on the problems we have found to extract a linguistically (and computationally) sound grammar and approaches to handle them.

Using the linguistic knowledge in BulTreeBank for the selection of the correct parses

Ninth International Workshop on Treebanks …, 2010

The Russian syntactic treebank SynTagRus is annotated with dependency structures in line with the Meaning-Text Theory (MTT). In order to benefit from the detailed syntactic annotation in SynTagRus and facilitate the development of a Russian Resource Grammar (RRG) in the framework of Head-driven Phrase Structure Grammar (HPSG), we need to convert the dependency structures into HPSG derivation trees. Our pilot study has shown that many of the constructions can be converted systematically with simple rules. In order to extend the depth and coverage of this conversion, we need to implement conversion heuristics that produce linguistically sound HPSG derivations. As a result we obtain a structured set of correspondences between MTT surface syntactic relations and HPSG phrasal types, which enable the cross-theoretical transfer of insightful syntactic analyses and formalized deep linguistic knowledge. The converted treebank SynTagRus++ is annotated with HPSG structures and of crucial importance to the RRG under development, as our goal is to ensure an optimal and efficient grammar engineering cycle through dynamic coupling of the treebank and the grammar. * We are grateful to Leonid L. Iomdin for providing us with access to the SynTagRus dependency treebank and for helpful answers to annotation-related questions.

Conversion of a Russian dependency treebank into HPSG derivations

2010

The Russian syntactic treebank SynTagRus is annotated with dependency structures in line with the Meaning-Text Theory (MTT). In order to benefit from the detailed syntactic annotation in SynTagRus and facilitate the development of a Russian Resource Grammar (RRG) in the framework of Head-driven Phrase Structure Grammar (HPSG), we need to convert the dependency structures into HPSG derivation trees. Our pilot study has shown that many of the constructions can be converted systematically with simple rules. In order to extend the depth and coverage of this conversion, we need to implement conversion heuristics that produce linguistically sound HPSG derivations. As a result we obtain a structured set of correspondences between MTT surface syntactic relations and HPSG phrasal types, which enable the cross-theoretical transfer of insightful syntactic analyses and formalized deep linguistic knowledge. The converted treebank SynTagRus++ is annotated with HPSG structures and of crucial impor...

LTAG-spinal and the Treebank: A new resource for incremental, dependency and semantic parsing.

We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Unlike in traditional LTAG, subcategorization frames and the argument-adjunct distinction are left underspecified in LTAG-spinal. LTAG-spinal with adjunction constraints is weakly equivalent to LTAG. The LTAG-spinal formalism is used to extract an LTAG-spinal Treebank from the Penn Treebank with Propbank annotation. Based on Propbank annotation, predicate coordination and LTAG adjunction structures are successfully extracted. The LTAG-spinal Treebank makes explicit semantic relations that are implicit or absent from the original PTB. LTAG-spinal provides a very desirable resource for statistical LTAG parsing, incremental parsing, dependency parsing, and semantic parsing. This treebank has been successfully used to train an incremental LTAG-spinal parser and a bidirectional LTAG dependency parser.