Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293877269> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4293877269 abstract "Traditional natural language parsers are based on rewrite rule systems developed in an arduous, time-consuming manner by grammarians. A majority of the grammarian's efforts are devoted to the disambiguation process, first hypothesizing rules which dictate constituent categories and relationships among words in ambiguous sentences, and then seeking exceptions and corrections to these rules. In this work, I propose 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. Based on distributionally-derived and linguistically-based features of language, this parser acquires a set of statistical decision trees which assign a probability distribution on the space of parse trees given the input sentence. These decision trees take advantage of significant amount of contextual information, potentially including all of the lexical information in the sentence, to produce highly accurate statistical models of the disambiguation process. By basing the disambiguation criteria selection on entropy reduction rather than human intuition, this parser development method is able to consider more sentences than a human grammarian can when making individual disambiguation rules. In experiments between a parser, acquired using this statistical framework, and a grammarian's rule-based parser, developed over a ten-year period, both using the same training material and test sentences, the decision tree parser significantly outperformed the grammar-based parser on the accuracy measure which the grammarian was trying to maximize, achieving an accuracy of 78% compared to the grammar-based parser's 69%." @default.
- W4293877269 created "2022-09-01" @default.
- W4293877269 creator A5007446699 @default.
- W4293877269 date "1994-05-03" @default.
- W4293877269 modified "2023-09-27" @default.
- W4293877269 title "Natural Language Parsing as Statistical Pattern Recognition" @default.
- W4293877269 doi "https://doi.org/10.48550/arxiv.cmp-lg/9405009" @default.
- W4293877269 hasPublicationYear "1994" @default.
- W4293877269 type Work @default.
- W4293877269 citedByCount "0" @default.
- W4293877269 crossrefType "posted-content" @default.
- W4293877269 hasAuthorship W4293877269A5007446699 @default.
- W4293877269 hasBestOaLocation W42938772691 @default.
- W4293877269 hasConcept C118364021 @default.
- W4293877269 hasConcept C138885662 @default.
- W4293877269 hasConcept C146810361 @default.
- W4293877269 hasConcept C154945302 @default.
- W4293877269 hasConcept C177264268 @default.
- W4293877269 hasConcept C186644900 @default.
- W4293877269 hasConcept C195324797 @default.
- W4293877269 hasConcept C199360897 @default.
- W4293877269 hasConcept C204321447 @default.
- W4293877269 hasConcept C26022165 @default.
- W4293877269 hasConcept C2777530160 @default.
- W4293877269 hasConcept C2781466058 @default.
- W4293877269 hasConcept C41008148 @default.
- W4293877269 hasConcept C41895202 @default.
- W4293877269 hasConcept C42560504 @default.
- W4293877269 hasConcept C53893814 @default.
- W4293877269 hasConcept C67621940 @default.
- W4293877269 hasConcept C9679016 @default.
- W4293877269 hasConcept C97212296 @default.
- W4293877269 hasConceptScore W4293877269C118364021 @default.
- W4293877269 hasConceptScore W4293877269C138885662 @default.
- W4293877269 hasConceptScore W4293877269C146810361 @default.
- W4293877269 hasConceptScore W4293877269C154945302 @default.
- W4293877269 hasConceptScore W4293877269C177264268 @default.
- W4293877269 hasConceptScore W4293877269C186644900 @default.
- W4293877269 hasConceptScore W4293877269C195324797 @default.
- W4293877269 hasConceptScore W4293877269C199360897 @default.
- W4293877269 hasConceptScore W4293877269C204321447 @default.
- W4293877269 hasConceptScore W4293877269C26022165 @default.
- W4293877269 hasConceptScore W4293877269C2777530160 @default.
- W4293877269 hasConceptScore W4293877269C2781466058 @default.
- W4293877269 hasConceptScore W4293877269C41008148 @default.
- W4293877269 hasConceptScore W4293877269C41895202 @default.
- W4293877269 hasConceptScore W4293877269C42560504 @default.
- W4293877269 hasConceptScore W4293877269C53893814 @default.
- W4293877269 hasConceptScore W4293877269C67621940 @default.
- W4293877269 hasConceptScore W4293877269C9679016 @default.
- W4293877269 hasConceptScore W4293877269C97212296 @default.
- W4293877269 hasLocation W42938772691 @default.
- W4293877269 hasOpenAccess W4293877269 @default.
- W4293877269 hasPrimaryLocation W42938772691 @default.
- W4293877269 hasRelatedWork W120840286 @default.
- W4293877269 hasRelatedWork W158198953 @default.
- W4293877269 hasRelatedWork W1806995473 @default.
- W4293877269 hasRelatedWork W1908013816 @default.
- W4293877269 hasRelatedWork W1924403233 @default.
- W4293877269 hasRelatedWork W2040290555 @default.
- W4293877269 hasRelatedWork W2162584824 @default.
- W4293877269 hasRelatedWork W2167662847 @default.
- W4293877269 hasRelatedWork W2502722637 @default.
- W4293877269 hasRelatedWork W4293877269 @default.
- W4293877269 isParatext "false" @default.
- W4293877269 isRetracted "false" @default.
- W4293877269 workType "article" @default.