Osborne, M., Learning Unification-Based Natural Language Grammars, PhD. Thesis, University of York, 1994. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A Model for the Acquisition of New Lexical Entries - Castelnovo (1997) (Correct)
....both general purpose and tailored to particular lexical resources ( EK95] pag. 6) The aim of this contribution is to describe a model for the automatic acquisition of new lexical entries which can be considered as one such lexical engineering tool . The model, which is based on the work of [Osb94] and [Rus93] allows the acquisition of new lexical entries by resorting to resources which can be assumed to be already available in a NLP system, namely: i) a general theory of grammar; ii) a suitable parsing algorithm and (iii) an application independent core lexicon structured according to ....
Osborne, M., Learning Unification-Based Natural Language Grammars, PhD. Thesis, University of York, 1994.
.8 Summary of Findings - Our Main Findings (Correct)
....For some cases, the grammar will undergenerate; for other cases, the sentence may contain extra words, or missing words. Mellish presents applicable work dealing with missing words and simple forms of ill formed constructs (Mellish, 1989) Osborne describes work dealing with undergeneration (Osborne, 1994). Future work will extend ANLT with components that deal with these aspects of processing unrestricted language. We believe that our use of relaxation preserves the robustness (within limits) approach used in this work: only certain sentences can be relaxed; others are best rejected. 8.3 Parser ....
Osborne, M. (1994). Learning Unification-based Natural Language Grammars. Ph.D. Thesis, University of York, September 1994.
Can Punctuation Help Learning? - Osborne (1996) (1 citation) Self-citation (Osborne) (Correct)
....learning, for example, is complete in the sense that such a learner is always capable of making a decision, but inadequate at learning natural language grammars (Gold 1967) Model based learning is capable of learning such grammars, but in practice suffers from incompleteness. In previous work (Osborne Bridge 1994b; 1994a; Osborne 1994) we have shown how using both learners together produces qualitatively better grammars than are produced when using either learner in isolation. Model based learning compensated for the inadequacy of data driven learning, whilst data driven learning reduced the ....
....in the sense that such a learner is always capable of making a decision, but inadequate at learning natural language grammars (Gold 1967) Model based learning is capable of learning such grammars, but in practice suffers from incompleteness. In previous work (Osborne Bridge 1994b; 1994a; Osborne 1994) we have shown how using both learners together produces qualitatively better grammars than are produced when using either learner in isolation. Model based learning compensated for the inadequacy of data driven learning, whilst data driven learning reduced the incompleteness problem facing the ....
[Article contains additional citation context not shown here]
Osborne, M. 1994. Learning Unification-based Natural Language Grammars. Ph.D. Dissertation, University of York.
Parsing Computer Manuals using a Robust Alvey Natural.. - Miles Osborne Department (1995) Self-citation (Osborne) (Correct)
....sentences. For some cases, the grammar will undergenerate; for other cases, the sentence may contain extra words, or missing words. Mellish presents applicable work dealing with missing words and simple forms of ill formed constructs [Mel89] Osborne describes work dealing with undergeneration [Osb94] Future work will extend the ANLT with components that deal with these aspects of processing unrestricted language. We believe that our use of relaxation preserves the robustness (within limits) approach used in this work: only certain sentences can be relaxed; others are best rejected. 3 ....
Miles Osborne. Learning Unification-based Natural Language Grammars. PhD thesis, University of York, September 1994. 15
More for Less: Learning a Wide Covering Grammar From a Small.. - Osborne, Bridge Self-citation (Osborne) (Correct)
.... for less: learning a wide covering grammar from a small training set Miles Osborne and Derek Bridge Department of Computer Science, University of York, Heslington, York YO1 5DD, U. K. fmiles,dgbg minster.york.ac.uk Abstract This paper describes a grammar learning system which combines model based and data driven learning within a single framework. Results from learning ....
Miles Osborne. Learning Unification-based Natural Language Grammars. PhD thesis, University of York, forthcoming. R. A. Sharman, F. Jelinek, and R. L. Mercer. Generating a grammar for statistical training. In Proceedings of the IBM Conference on Natural Language Processing, 1988.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC