Skip to search formSkip to main contentSkip to account menu
- Corpus ID: 17402234
@inproceedings{Sharman2005GeneratingAG, title={Generating a grammar for statistical training}, author={Richard A. Sharman and Science Research Centre and Winchester Sharman and Venta Y Jelinek and T J Wacson Research and Yorktown He£ghcs and Jelinek At and Yktvmv R Hercer and T J Wagson Research}, booktitle={Human Language Technology - The Baltic Perspectiv}, year={2005}, url={https://api.semanticscholar.org/CorpusID:17402234}}- R. Sharman, S. Centre, T. J. W. Research
- Published in Human Language Technology… 2005
- Computer Science, Linguistics
Parsing sentences of a Natural LanguaF(NL) is an essential requiRrnent for a variety of NL a p plications, and has been extensively studied. In particular, the sort of tasks which it would be desirable to do, include the ability to tag each word with its part-of-sin:h; to delineate with brackets, and label with a category name, each syntactic phrase; and to be able to adapt to different types of source material. Despite some 30 years of active research Performing these tasks with a high degree…
56 Citations
3
15
7
2
Topics
P-CFG (opens in a new tab)Category Names (opens in a new tab)Part-of-speech (opens in a new tab)
56 Citations
- G. J. Wilms
- 1996
Computer Science, Linguistics
This dissertation shows how the process of fitting a lexicalized grammar to a domain can be automated to a great extent by using a hybrid system that combines traditional knowledge-based techniques with a corpus-based approach.
- 7
- PDF
- Ezra BlackStephen EubankHideki KashiokaDavid M. Magerman
- 1997
Computer Science, Linguistics
VLC
Summary A grammar-based probabilistic parser is described, and experimental results are presented for the parser as trained and tested on a 676,000-word, highly varied treebank of unrestricted…
- 1
- Ted Briscoe
- 1996
Computer Science, Linguistics
Parsing systems able to analyse natural language text robustly and accurately at an appropriate level of detail would be of great value in computer applications ranging from speech synthesis and…
- 10
- PDF
- John A. CarrollTed Briscoe
- 2017
Computer Science, Linguistics
We have developed a prototype system for syntactic parsing of corpus text based on a wide-coverage unification-based grammar of English and domain-independent statistical techniques for selecting the…
- PDF
- Eric Brill
- 1993
Computer Science
HLT
A new technique for grammar induction that is very simple, it requires only a very small set of transformations, learning proceeds quickly and achieves a high degree of accuracy, and only a very small training corpUs is necessary.
- 61
- PDF
- John A. CarrollTed Briscoe
- 1992
Computer Science
A domain-independent solution based on integrating statistical Markov modelling techniques, which offer the potential for rapid tuning to different sublanguages / corpora on the basis of supervised training, with linguistically-adequate grammatical models, capable of returning analyses detailed enough to support semantic interpretation.
- 32
- PDF
- Ted BriscoeJohn A. Carroll
- 1993
Computer Science
CL
The construction of a very wide-coverage probabilistic parsing system for natural language (NL) based on LR parsing techniques, intended to rank the large number of syntactic analyses produced by NL grammars according to the frequency of occurrence of the individual rules deployed in each analysis.
- 276
- Highly Influenced
- PDF
- P. Jacobs
- 1992
Computer Science
A good approach is to focus linguistic analysis on relations that directly impact the semantic results, detaching these relations from the complete constituents to which they belong, which results in a faster, more robust, and potentially more accura.
- PDF
- David M. Magerman
- 1994
Computer Science, Linguistics
ArXiv
This work proposes an automatic method for acquiring a statistical parser from a set of parsed sentences which takes advantage of some initial linguistic input, but avoids the pitfalls of the iterative and seemingly endless grammar development process.
- 279
- Highly Influenced
- PDF
- Eric Brill
- 1993
Computer Science
IWPT
A transformational grammar is automatically learned that is capable of accurately parsing text into binary-branching syntactic trees, and a set of simple structural transformations are applied to reduce the number of errors.
- 62
- PDF
...
...
12 References
- J. Baker
- 1979
Computer Science
This paper presents a generalization of these algorithms to certain denumerable‐state, hidden Markov processes that permits automatic training of the stochastic analog of an arbitrary context free grammar.
- 669
- PDF
- C. Wetherell
- 1980
Computer Science, Mathematics
CSUR
Context-free languages are commonly used to describe the structure of programming ~ languages. However many interesting problems involve not just a language's structure but also the actual usage of…
- 175
- PDF
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers
![[PDF] Generating a grammar for statistical training | Semantic Scholar (2024)](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/h8AAvMB+NzmkbcAAAAASUVORK5CYII=)