Matches in ScholarlyData for { ?s ?p ?o. }
- item-1 hasContent mukda-suktarachan.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent dussadee-thamvijit.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent daoyos-noikongka.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent panita-yongyuth.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent puwarat-pavaputanont-na-mahasarakham.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent asanee-kawtrakul.
- item-6 next item-7.
- item-6 previous item-5.
- item-7 type ListItem.
- item-7 hasContent asanee-kawtrakul.
- item-7 next item-8.
- item-7 previous item-6.
- item-8 type ListItem.
- item-8 hasContent margherita-sini.
- item-8 previous item-7.
- 625 creator benjamin-farber.
- 625 creator dayne-freitag.
- 625 creator nizar-habash.
- 625 creator owen-rambow.
- 625 type InProceedings.
- 625 label "Improving NER in Arabic Using a Morphological Tagger".
- 625 sameAs 625.
- 625 abstract "We discuss a named entity recognition system for Arabic, and show how we incorporated the information provided by MADA, a full morphological tagger which uses a morphological analyzer. Surprisingly, the relevant features used are the capitalization of the English gloss chosen by the tagger, and the fact that an analysis is returned (that a word is not OOV to the morphological analyzer). The use of the tagger also improves over a third system which just uses a morphological analyzer, yielding a 14\% reduction in error over the baseline. We conduct a thorough error analysis to identify sources of success and failure among the variations, and show that by combining the systems in simple ways we can significantly influence the precision-recall trade-off.".
- 625 hasAuthorList authorList.
- 625 hasTopic Linguistics.
- 625 isPartOf proceedings.
- 625 keyword "Lexicon, lexical database".
- 625 keyword "Morphology".
- 625 keyword "Named Entity recognition".
- 625 title "Improving NER in Arabic Using a Morphological Tagger".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasLastItem item-4.
- item-1 type ListItem.
- item-1 hasContent benjamin-farber.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent dayne-freitag.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent nizar-habash.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent owen-rambow.
- item-4 previous item-3.
- 626 creator jacques-chauche.
- 626 creator violaine-prince.
- 626 type InProceedings.
- 626 label "Building a Bilingual Representation of the Roget Thesaurus for French to English Machine Translation".
- 626 sameAs 626.
- 626 abstract "This paper describes a solution to lexical transfer as a trade-off between a dictionary and an ontology. It shows its association to a translation tool based on morpho-syntactical parsing of the source language. It is based on the English Roget Thesaurus and its equivalent, the French Larousse Thesaurus, in a computational framework. Both thesaurii are transformed into vector spaces, and all monolingual entries are represented as vectors, with 1,000 components for English and 873 for French. The indexing concepts of the respective thesaurii are the generation families of the vector spaces. A bilingual data structure transforms French entries into vectors in the English space, by using their equivalencies representations. Word sense disambiguation consists in choosing the appropriate vector among these bilingual vectors, by computing the contextualized vector of a given word in its source sentence, wading it in the English vector space, and computing the closest distance to the different entries in the bilingual data structure beginning with the same source string (i.e. French word). The process has been experimented on a 20,000 words extract of a French novel, Le Petit Prince, and lexical transfer results were found quite encouraging with a recall of 71% and a precision of 86%.".
- 626 hasAuthorList authorList.
- 626 hasTopic Linguistics.
- 626 isPartOf proceedings.
- 626 keyword "Lexicon, lexical database".
- 626 keyword "Machine Translation, SpeechToSpeech Translation".
- 626 keyword "Multilinguality".
- 626 title "Building a Bilingual Representation of the Roget Thesaurus for French to English Machine Translation".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent violaine-prince.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent jacques-chauche.
- item-2 previous item-1.
- 627 creator david-martins-de-matos.
- 627 creator nuno-j-mamede.
- 627 creator paula-cristina-vaz.
- 627 type InProceedings.
- 627 label "Using Lexical Acquisition to Enrich a Predicate Argument Reusable Database".
- 627 sameAs 627.
- 627 abstract "The work described in this paper aims to enrich the noun classifications of an existing database of lexical resources (de Matos and Ribeiro, 2004) adding missing information such as semantic relations. Relations are extracted from an annotated and manually corrected corpus. Semantic relations added to the database are retrieved from noun-appositive relations found in the corpus. The method uses clustering to generate labeled sets of words with hypernym relations between set label and set elements.".
- 627 hasAuthorList authorList.
- 627 hasTopic Linguistics.
- 627 isPartOf proceedings.
- 627 keyword "Acquisition, Machine Learning".