Evaluating two methods for Treebank grammar compaction

Krotov, Alexander; Hepple, Mark; Gaizauskas, Robert; Wilks, Yorick

doi:10.1017/s1351324900002308

Cited by 4 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To integrate and experiment with a PCFG backbone we developed initial PCFG extraction tools that can process treebanks of the Penn Treebank format (Marcus et al, 1993). For languages that have existing treebanks such as English and Mandarin Chinese, 17 we can generate a PCFG and compact the rules for the parser (Krotov et al, 1999).…”

Section: Development Planmentioning

confidence: 99%

Preliminary results from the Free Linguistic Environment project

Ćavar¹,

Moe²,

Hu³

et al. 2016

hpsg

View full text Add to dashboard Cite

The Free Linguistic Environment (FLE) project focuses on the development of an open and free library of natural language processing functions and a grammar engineering platform for Lexical Functional Grammar (LFG) and related grammar frameworks. In its present state the code-base of FLE contains basic essential elements for LFG-parsing. It uses finite-state-based morphological analyzers and syntactic unification parsers to generate parse-trees and related functional representations for input sentences based on a grammar. It can process a variety of grammar formalisms, which can be used independently or serve as backbones for the LFG parser. Among the supported formalisms are Context-free Grammars (CFG), Probabilistic Contextfree Grammars (PCFG), and all formal grammar components of the XLEgrammar formalism. The current implementation of the LFG-parser includes the possibility to use a PCFG backbone to model probabilistic c-structures. It also includes f-structure representations that allow for the specification or calculation of probabilities for complete f-structure representations, as well as for sub-paths in f-structure trees. Given these design features, FLE enables various forms of probabilistic modeling of c-structures and f-structures for input or output sentences that go beyond the capabilities of other technologies based on the LFG framework.

show abstract

Section: Development Planmentioning

confidence: 99%

Preliminary results from the Free Linguistic Environment project

Ćavar¹,

Moe²,

Hu³

et al. 2016

hpsg

View full text Add to dashboard Cite

show abstract

“…the rate at which new tags are discovered as more text is processed was examined (see e.g. Krotov et al (1999) for further explanation of accession rates). One might expect that as more text is processed, the number of new tags added per text will be smaller.…”

Section: How Much Training Data Is Necessary?mentioning

confidence: 99%

A resource-light approach to morpho-syntactic tagging

Feldman¹,

Hana²

2010

View full text Add to dashboard Cite

Morpho-syntactic tagging is the process of assigning part of speech (POS), case, number, gender, and other morphological information to each word in a corpus. Morpho-syntactic tagging is an important step in natural language processing. Corpora that have been morphologically tagged are very useful both for linguistic research, e.g. finding instances or frequencies of particular constructions in large corpora, and for further computational processing, such as syntactic parsing, speech recognition, stemming, and word-sense disambiguation, among others. Despite the importance of morphological tagging, there are many languages that lack annotated resources. This is almost inevitable because these resources are costly to create. But, as described in this thesis, it is possible to avoid this expense. This thesis describes a method for transferring annotation from a morphologically annotated corpus of a source language to a corpus of a related target language. Unlike unsupervised approaches that do not require annotated data at all and, as a consequence, lack precision, the approach proposed in this dissertation relies on linguistic knowledge, but avoids large-scale grammar engineering. The approach needs neither a parallel corpus nor a bilingual lexicon, and requires much less linguistic labor than the standard technology. This dissertation describes experiments with Russian, Czech, Polish, Spanish, Portuguese, and Catalan. However, the general method proposed can be applied to any fusional language.

show abstract

Learning grammars for different parsing tasks by partition search

Belz

2002

Proceedings of the 19th International Conference on Computational Linguistics -

View full text Add to dashboard Cite

This paper describes a comparative application of Grammar Learning by Partition Search to four different learning tasks: deep parsing, NP identification, flat phrase chunking and NP chunking. In the experiments, base grammars were extracted from a treebank corpus. From this starting point, new grammars optimised for the different parsing tasks were learnt by Partition Search. No lexical information was used. In half of the experiments, local structural context in the form of parent phrase category information was incorporated into the grammars. Results show that grammars which contain this information outperform grammars which do not by large margins in all tests for all parsing tasks. It makes the biggest difference for deep parsing, typically corresponding to an improvement of around 5%. Overall, Partition Search with parent phrase category information is shown to be a successful method for learning grammars optimised for a given parsing task, and for minimising grammar size. The biggest margin of improvement over a base grammar was a 5.4% increase in the F-Score for deep parsing. The biggest size reductions were 93.5% fewer nonterminals (for NP identification), and 31.3% fewer rules (for XP chunking

show abstract

Evaluating two methods for Treebank grammar compaction

Cited by 4 publications

References 13 publications

Preliminary results from the Free Linguistic Environment project

Preliminary results from the Free Linguistic Environment project

A resource-light approach to morpho-syntactic tagging

Learning grammars for different parsing tasks by partition search

Contact Info

Product

Resources

About