Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385342823> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4385342823 endingPage "19" @default.
- W4385342823 startingPage "1" @default.
- W4385342823 abstract "Neural approaches, which are currently state-of-the-art in many areas, have contributed significantly to the exciting advancements in machine translation. However, Neural Machine Translation (NMT) requires a substantial quantity and good quality parallel training data to train the best model. A large amount of training data, in turn, increases the underlying vocabulary exponentially. Therefore, several proposed methods have been devised for relatively limited vocabulary due to constraints of computing resources such as system memory. Encoding words as sequences of subword units for so-called open-vocabulary translation is an effective strategy for solving this problem. However, the conventional methods for splitting words into subwords focus on statistics-based approaches that mainly conform to agglutinative languages. In these languages, the morphemes have relatively clean boundaries. These methods still need to be thoroughly investigated for their applicability to fusion languages, which is the main focus of this article. Phonological and orthographic processes alter the borders of constituent morphemes of a word in fusion languages. Therefore, it makes it difficult to distinguish the actual morphemes that carry syntactic or semantic information from the word’s surface form, the form of the word as it appears in the text. We, thus, resorted to a word segmentation method that segments words by restoring the altered morphemes. We also compared conventional and morpheme-based NMT subword models. We could prove that morpheme-based models outperform conventional subword models on a benchmark dataset." @default.
- W4385342823 created "2023-07-29" @default.
- W4385342823 creator A5061881907 @default.
- W4385342823 creator A5075663234 @default.
- W4385342823 date "2023-09-22" @default.
- W4385342823 modified "2023-09-24" @default.
- W4385342823 title "Morpheme-Based Neural Machine Translation Models for Low-Resource Fusion Languages" @default.
- W4385342823 cites W1533169541 @default.
- W4385342823 cites W1760821052 @default.
- W4385342823 cites W1995875735 @default.
- W4385342823 cites W1998503232 @default.
- W4385342823 cites W2027489130 @default.
- W4385342823 cites W2181176782 @default.
- W4385342823 cites W2183341477 @default.
- W4385342823 cites W2531207078 @default.
- W4385342823 cites W2611598898 @default.
- W4385342823 cites W2624521690 @default.
- W4385342823 cites W2796108585 @default.
- W4385342823 cites W2806532810 @default.
- W4385342823 cites W2962784628 @default.
- W4385342823 cites W2963532001 @default.
- W4385342823 cites W2964053711 @default.
- W4385342823 cites W2971005778 @default.
- W4385342823 cites W3001816066 @default.
- W4385342823 cites W3014784959 @default.
- W4385342823 cites W3037312903 @default.
- W4385342823 cites W3106889297 @default.
- W4385342823 cites W3113488190 @default.
- W4385342823 cites W3127800805 @default.
- W4385342823 cites W3128651145 @default.
- W4385342823 cites W3153847883 @default.
- W4385342823 cites W3175955584 @default.
- W4385342823 cites W3198189804 @default.
- W4385342823 cites W4249773576 @default.
- W4385342823 doi "https://doi.org/10.1145/3610773" @default.
- W4385342823 hasPublicationYear "2023" @default.
- W4385342823 type Work @default.
- W4385342823 citedByCount "0" @default.
- W4385342823 crossrefType "journal-article" @default.
- W4385342823 hasAuthorship W4385342823A5061881907 @default.
- W4385342823 hasAuthorship W4385342823A5075663234 @default.
- W4385342823 hasBestOaLocation W43853428231 @default.
- W4385342823 hasConcept C120665830 @default.
- W4385342823 hasConcept C121332964 @default.
- W4385342823 hasConcept C130597682 @default.
- W4385342823 hasConcept C13280743 @default.
- W4385342823 hasConcept C138885662 @default.
- W4385342823 hasConcept C154945302 @default.
- W4385342823 hasConcept C165297611 @default.
- W4385342823 hasConcept C185798385 @default.
- W4385342823 hasConcept C192209626 @default.
- W4385342823 hasConcept C203005215 @default.
- W4385342823 hasConcept C204321447 @default.
- W4385342823 hasConcept C205649164 @default.
- W4385342823 hasConcept C24687705 @default.
- W4385342823 hasConcept C2777601683 @default.
- W4385342823 hasConcept C28490314 @default.
- W4385342823 hasConcept C41008148 @default.
- W4385342823 hasConcept C41895202 @default.
- W4385342823 hasConcept C80875076 @default.
- W4385342823 hasConcept C90805587 @default.
- W4385342823 hasConceptScore W4385342823C120665830 @default.
- W4385342823 hasConceptScore W4385342823C121332964 @default.
- W4385342823 hasConceptScore W4385342823C130597682 @default.
- W4385342823 hasConceptScore W4385342823C13280743 @default.
- W4385342823 hasConceptScore W4385342823C138885662 @default.
- W4385342823 hasConceptScore W4385342823C154945302 @default.
- W4385342823 hasConceptScore W4385342823C165297611 @default.
- W4385342823 hasConceptScore W4385342823C185798385 @default.
- W4385342823 hasConceptScore W4385342823C192209626 @default.
- W4385342823 hasConceptScore W4385342823C203005215 @default.
- W4385342823 hasConceptScore W4385342823C204321447 @default.
- W4385342823 hasConceptScore W4385342823C205649164 @default.
- W4385342823 hasConceptScore W4385342823C24687705 @default.
- W4385342823 hasConceptScore W4385342823C2777601683 @default.
- W4385342823 hasConceptScore W4385342823C28490314 @default.
- W4385342823 hasConceptScore W4385342823C41008148 @default.
- W4385342823 hasConceptScore W4385342823C41895202 @default.
- W4385342823 hasConceptScore W4385342823C80875076 @default.
- W4385342823 hasConceptScore W4385342823C90805587 @default.
- W4385342823 hasIssue "9" @default.
- W4385342823 hasLocation W43853428231 @default.
- W4385342823 hasOpenAccess W4385342823 @default.
- W4385342823 hasPrimaryLocation W43853428231 @default.
- W4385342823 hasRelatedWork W1512718085 @default.
- W4385342823 hasRelatedWork W193726211 @default.
- W4385342823 hasRelatedWork W2142990792 @default.
- W4385342823 hasRelatedWork W2167662847 @default.
- W4385342823 hasRelatedWork W2950091200 @default.
- W4385342823 hasRelatedWork W3093542232 @default.
- W4385342823 hasRelatedWork W3155519294 @default.
- W4385342823 hasRelatedWork W4317502730 @default.
- W4385342823 hasRelatedWork W4382052914 @default.
- W4385342823 hasRelatedWork W2610387714 @default.
- W4385342823 hasVolume "22" @default.
- W4385342823 isParatext "false" @default.
- W4385342823 isRetracted "false" @default.
- W4385342823 workType "article" @default.