Syntactic and Semantic Impact of Prepositions in Machine Translation : An Empirical Study of French-English Translation of Prepositions ‘à’, ‘de’ and ‘en’
| Autor: | Violaine Prince |
|---|---|
| Přispěvatelé: | Exploration et exploitation de données textuelles (TEXTE), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
060201 languages & linguistics
Dependency (UML) Point (typography) Machine translation business.industry Computer science 06 humanities and the arts 02 engineering and technology Semantics computer.software_genre Syntax Set (abstract data type) [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing Dependency grammar 0602 languages and literature 0202 electrical engineering electronic engineering information engineering Prepositions Machine aided translation 020201 artificial intelligence & image processing Artificial intelligence business Heuristics computer Natural language processing Natural Language Processing |
| Zdroj: | Human Language Technology. Challenges for Computer Science and Linguistics 8th Language and Technology Conference, LTC 2017, Poznań, Poland, November 17–19, 2017, Revised Selected Papers 8th Language and Technology Conference (LTC 2017) Human Language Technology. Challenges for Computer Science and Linguistics 8th Language and Technology Conference, LTC 2017, Poznań, Poland, November 17–19, 2017, Revised Selected Papers, 12598, pp.273-287, 2020, Lecture Notes in Computer Science, 978-3-030-66526-5. ⟨10.1007/978-3-030-66527-2_20⟩ Human Language Technology. Challenges for Computer Science and Linguistics ISBN: 9783030665265 LCT |
| DOI: | 10.1007/978-3-030-66527-2_20⟩ |
| Popis: | International audience; This paper presents a study about ambiguous French prepositions, stressing out their roles as dependencies introducers, in order to derive some translation heuristics into English, based on a FrenchEnglish set of parallel texts. These heuristics are formulated out of statistical observations and use some up-to-date results in Machine Translation (MT). Their originality mostly relies upon two items: (1) The importance given to syntax and dependency relations, along with lexicons, the latter being well browsed by the present literature in the domain (2) The existence of intrinsic semantics in prepositions, something rather discarded in NLP literature devoted to statistical MT, that tends to point at the most appropriate translation. An experiment has been run on corpora in both languages, using a dependency parser in the source language, and results looked to be encouraging for a “step by step approach” for MT improvement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|