Matches in SemOpenAlex for { <https://semopenalex.org/work/W2101585636> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2101585636 abstract "Discriminative approaches for word alignment have gained popularity in recent years because of the flexibility that they offer for using a large variety of features and combining information from various sources. But, the models proposed in the past have not been able to make much use of features that capture the likelihood of an alignment structure (the set of alignment links) and the syntactic divergence between sentences in the parallel text. This is primarily because of the limitation of their search techniques. In this paper, we propose a generic discriminative re-ranking approach for word alignment which allows us to make use of structural features effectively. These features are particularly useful for language pairs with high structural divergence (like English-Hindi, English-Japanese). We have shown that by using the structural features, we have obtained a decrease of 2.3% in the absolute value of alignment error rate (AER). When we add the cooccurence probabilities obtained from IBM model-4 to our features, we achieved the best AER (50.50) for the English-Hindi parallel corpus." @default.
- W2101585636 created "2016-06-24" @default.
- W2101585636 creator A5022203051 @default.
- W2101585636 creator A5048245391 @default.
- W2101585636 date "2007-01-01" @default.
- W2101585636 modified "2023-09-26" @default.
- W2101585636 title "Discriminative word alignment by learning the alignment structure and syntactic divergence between a language pair" @default.
- W2101585636 cites W1714704734 @default.
- W2101585636 cites W2038698865 @default.
- W2101585636 cites W2119224513 @default.
- W2101585636 cites W2122244345 @default.
- W2101585636 cites W2122922578 @default.
- W2101585636 cites W2124810114 @default.
- W2101585636 cites W2127686544 @default.
- W2101585636 cites W2140702357 @default.
- W2101585636 cites W2156985047 @default.
- W2101585636 cites W57248692 @default.
- W2101585636 doi "https://doi.org/10.3115/1626281.1626288" @default.
- W2101585636 hasPublicationYear "2007" @default.
- W2101585636 type Work @default.
- W2101585636 sameAs 2101585636 @default.
- W2101585636 citedByCount "7" @default.
- W2101585636 countsByYear W21015856362012 @default.
- W2101585636 countsByYear W21015856362013 @default.
- W2101585636 countsByYear W21015856362015 @default.
- W2101585636 crossrefType "proceedings-article" @default.
- W2101585636 hasAuthorship W2101585636A5022203051 @default.
- W2101585636 hasAuthorship W2101585636A5048245391 @default.
- W2101585636 hasBestOaLocation W21015856361 @default.
- W2101585636 hasConcept C137293760 @default.
- W2101585636 hasConcept C138885662 @default.
- W2101585636 hasConcept C153180895 @default.
- W2101585636 hasConcept C154945302 @default.
- W2101585636 hasConcept C162324750 @default.
- W2101585636 hasConcept C176217482 @default.
- W2101585636 hasConcept C189430467 @default.
- W2101585636 hasConcept C204321447 @default.
- W2101585636 hasConcept C207390915 @default.
- W2101585636 hasConcept C21547014 @default.
- W2101585636 hasConcept C2524010 @default.
- W2101585636 hasConcept C28490314 @default.
- W2101585636 hasConcept C33923547 @default.
- W2101585636 hasConcept C41008148 @default.
- W2101585636 hasConcept C41895202 @default.
- W2101585636 hasConcept C90805587 @default.
- W2101585636 hasConcept C97931131 @default.
- W2101585636 hasConceptScore W2101585636C137293760 @default.
- W2101585636 hasConceptScore W2101585636C138885662 @default.
- W2101585636 hasConceptScore W2101585636C153180895 @default.
- W2101585636 hasConceptScore W2101585636C154945302 @default.
- W2101585636 hasConceptScore W2101585636C162324750 @default.
- W2101585636 hasConceptScore W2101585636C176217482 @default.
- W2101585636 hasConceptScore W2101585636C189430467 @default.
- W2101585636 hasConceptScore W2101585636C204321447 @default.
- W2101585636 hasConceptScore W2101585636C207390915 @default.
- W2101585636 hasConceptScore W2101585636C21547014 @default.
- W2101585636 hasConceptScore W2101585636C2524010 @default.
- W2101585636 hasConceptScore W2101585636C28490314 @default.
- W2101585636 hasConceptScore W2101585636C33923547 @default.
- W2101585636 hasConceptScore W2101585636C41008148 @default.
- W2101585636 hasConceptScore W2101585636C41895202 @default.
- W2101585636 hasConceptScore W2101585636C90805587 @default.
- W2101585636 hasConceptScore W2101585636C97931131 @default.
- W2101585636 hasLocation W21015856361 @default.
- W2101585636 hasOpenAccess W2101585636 @default.
- W2101585636 hasPrimaryLocation W21015856361 @default.
- W2101585636 hasRelatedWork W1964591498 @default.
- W2101585636 hasRelatedWork W2020540721 @default.
- W2101585636 hasRelatedWork W2090137133 @default.
- W2101585636 hasRelatedWork W2102607778 @default.
- W2101585636 hasRelatedWork W2110418293 @default.
- W2101585636 hasRelatedWork W2369308426 @default.
- W2101585636 hasRelatedWork W2373222038 @default.
- W2101585636 hasRelatedWork W2435275165 @default.
- W2101585636 hasRelatedWork W3107474891 @default.
- W2101585636 hasRelatedWork W61141208 @default.
- W2101585636 isParatext "false" @default.
- W2101585636 isRetracted "false" @default.
- W2101585636 magId "2101585636" @default.
- W2101585636 workType "article" @default.