Searching for authors named Gregory Grefenstette – sorted by Relevance.

Order by: Citations | Year (Descending) | Year (Ascending) | Recency

Try your query at: Scholar | Yahoo! | Ask | Bing | CSB

28 documents found, showing 1 through 10. Next 10 →

Light Parsing as Finite State Filtering
by Gregory Grefenstette — 1996 — In A. Kornai (Eds.), Extended Finite State Models of Language
…. For a number of language processing tasks, such as information retrieval and information extraction tasks, pertinent information can be extracted from text without doing a full parse of the individual sentences. The most common restriction of the parser is to adopt a non-recursive model of the lan…
Cited by 3 (0 self) – Add To MetaCart

Evaluation Techniques for Automatic Semantic Extraction: Comparing Syntactic and Window Based Approaches
by Gregory Grefenstette — 1993
…As large on-line corpora become more prewlent, a number of attempts have been made to automatically extract thesaurus-like relations directly from text using knowledge poor methods. In the absence of any specific application, comparing the results of these attempts is difficult. Here we propose an e…
Cited by 34 (0 self) – Add To MetaCart

SQLET: Short Query Linguistic Expansion Techniques, Palliating One-Word Queries by Providing Intermediate Structure to Text
by Gregory Grefenstette — 1997 — In Proceedings of the RIAO’97
…Most people using the WWW try to find information using one or two word queries. The information retrieval systems derived from research models were designed for longer queries and do not provide an adequate response to the user's needs. On the other hand, recent advances in natural language process…
Cited by 19 (0 self) – Add To MetaCart

Corpus-Derived First, Second and Third-Order Word Affinities
by Gregory Grefenstette — 1994 — In Proceedings of Euralex
…A number of corpus-based extraction techniques have been successfully implemented which…
Cited by 23 (1 self) – Add To MetaCart

Sextant: Exploring Unexplored Contexts For Semantic Extraction from Syntactic Analysis
by Gregory Grefenstette — 1992 — in Proceedings of the 30st annual meeting of the Association for Computational Linguistics, ACL
…For a very long time, it has been considered that the only way of automatically extracting similar groups of words from a text collection for which no semantic information exists is to use document co-occurrence data. But, with robust syntactic parsers that are becoming more frequently available, sy…
Cited by 12 (1 self) – Add To MetaCart

Automatic Thesaurus Generation from Raw Text using Knowledge-Poor Techniques
by Gregory Grefenstette Rank, Gregory Grefenstette — 1993 — In Making Sense of Words. Ninth Annual Conference of the UW Centre for the New OED and text Research
…In addition to showing how lexical units are related within a field, domain-specific thesauri give an idea of what subjects are important to that field and are thus useful at many points in an information system. The major impediment to creation of thesauri has been the cost of their manual c…
Add To MetaCart

Translating Chinese Romanized name into Chinese idiographic characters via corpus and web validation
by Yiping Li, Gregory Grefenstette — 2005 — In Proceedings of CORIA 2005
…ABSTRACT. Cross-language information retrieval performance depends on the quality of the translation resources used to pass from a user’s source language query to target language documents. Translation lists of proper names are rare but vital resources for cross-language retrieval between languages …
Cited by 1 (0 self) – Add To MetaCart

Corpus-based Method for Automatic Identification of Support Verbs for Nominalizations
by Gregory Grefenstette, Simone Teufel — 1995 — In Proceedings of EACL, p. 98–103
…Nominalization is a highly productive phenomena in most languages.…
Cited by 21 (0 self) – Add To MetaCart

Estimation of English and non-English Language Use on the WWW
by Gregory Grefenstette, Julien Nioche — 2000 — In Recherche d’Information Assistée par Ordinateur (RIAO
…The World Wide Web has grown so big, in such an anarchic fashion, that it is difficult to describe. One of the evident intrinsic characteristics of the World Wide Web is its multilinguality. Here, we present a technique for estimating the size of a language-specific corpus given the frequency of com…
Cited by 38 (1 self) – Add To MetaCart

Showing 1 through 10. Next 10 →

Try your query at: Scholar | Yahoo! | Ask | Bing | CSB