Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198419977> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3198419977 endingPage "19" @default.
- W3198419977 startingPage "1" @default.
- W3198419977 abstract "The huge increase in social media use in recent years has resulted in new forms of social interaction, changing our daily lives. Due to increasing contact between people from different cultures as a result of globalization, there has also been an increase in the use of the Latin alphabet, and as a result a large amount of transliterated text is being used on social media. In this study, we propose a variety of character level sequence-to-sequence (seq2seq) models for normalizing noisy, transliterated text written in Latin script into Mongolian Cyrillic script, for scenarios in which there is a limited amount of training data available. We applied performance enhancement methods, which included various beam search strategies, N-gram-based context adoption, edit distance-based correction and dictionary-based checking, in novel ways to two basic seq2seq models. We experimentally evaluated these two basic models as well as fourteen enhanced seq2seq models, and compared their noisy text normalization performance with that of a transliteration model and a conventional statistical machine translation (SMT) model. The proposed seq2seq models improved the robustness of the basic seq2seq models for normalizing out-of-vocabulary (OOV) words, and most of our models achieved higher normalization performance than the conventional method. When using test data during our text normalization experiment, our proposed method which included checking each hypothesis during the inference period achieved the lowest word error rate (WER = 13.41%), which was 4.51% fewer errors than when using the conventional SMT method." @default.
- W3198419977 created "2021-09-13" @default.
- W3198419977 creator A5006132951 @default.
- W3198419977 creator A5024519127 @default.
- W3198419977 creator A5077234015 @default.
- W3198419977 creator A5090584209 @default.
- W3198419977 date "2021-09-01" @default.
- W3198419977 modified "2023-09-27" @default.
- W3198419977 title "Normalization of Transliterated Mongolian Words Using Seq2Seq Model with Limited Data" @default.
- W3198419977 cites W2119202242 @default.
- W3198419977 cites W2157331557 @default.
- W3198419977 cites W2402144811 @default.
- W3198419977 cites W2739688273 @default.
- W3198419977 cites W2757222607 @default.
- W3198419977 cites W2759029195 @default.
- W3198419977 cites W2944956301 @default.
- W3198419977 cites W2962733029 @default.
- W3198419977 cites W95844184 @default.
- W3198419977 doi "https://doi.org/10.1145/3464361" @default.
- W3198419977 hasPublicationYear "2021" @default.
- W3198419977 type Work @default.
- W3198419977 sameAs 3198419977 @default.
- W3198419977 citedByCount "1" @default.
- W3198419977 countsByYear W31984199772023 @default.
- W3198419977 crossrefType "journal-article" @default.
- W3198419977 hasAuthorship W3198419977A5006132951 @default.
- W3198419977 hasAuthorship W3198419977A5024519127 @default.
- W3198419977 hasAuthorship W3198419977A5077234015 @default.
- W3198419977 hasAuthorship W3198419977A5090584209 @default.
- W3198419977 hasConcept C136886441 @default.
- W3198419977 hasConcept C138885662 @default.
- W3198419977 hasConcept C144024400 @default.
- W3198419977 hasConcept C154945302 @default.
- W3198419977 hasConcept C19165224 @default.
- W3198419977 hasConcept C203005215 @default.
- W3198419977 hasConcept C204321447 @default.
- W3198419977 hasConcept C2776214188 @default.
- W3198419977 hasConcept C2777601683 @default.
- W3198419977 hasConcept C28490314 @default.
- W3198419977 hasConcept C40969351 @default.
- W3198419977 hasConcept C41008148 @default.
- W3198419977 hasConcept C41895202 @default.
- W3198419977 hasConcept C520968082 @default.
- W3198419977 hasConceptScore W3198419977C136886441 @default.
- W3198419977 hasConceptScore W3198419977C138885662 @default.
- W3198419977 hasConceptScore W3198419977C144024400 @default.
- W3198419977 hasConceptScore W3198419977C154945302 @default.
- W3198419977 hasConceptScore W3198419977C19165224 @default.
- W3198419977 hasConceptScore W3198419977C203005215 @default.
- W3198419977 hasConceptScore W3198419977C204321447 @default.
- W3198419977 hasConceptScore W3198419977C2776214188 @default.
- W3198419977 hasConceptScore W3198419977C2777601683 @default.
- W3198419977 hasConceptScore W3198419977C28490314 @default.
- W3198419977 hasConceptScore W3198419977C40969351 @default.
- W3198419977 hasConceptScore W3198419977C41008148 @default.
- W3198419977 hasConceptScore W3198419977C41895202 @default.
- W3198419977 hasConceptScore W3198419977C520968082 @default.
- W3198419977 hasIssue "6" @default.
- W3198419977 hasLocation W31984199771 @default.
- W3198419977 hasOpenAccess W3198419977 @default.
- W3198419977 hasPrimaryLocation W31984199771 @default.
- W3198419977 hasRelatedWork W2042474027 @default.
- W3198419977 hasRelatedWork W2118379766 @default.
- W3198419977 hasRelatedWork W2149655026 @default.
- W3198419977 hasRelatedWork W2171832244 @default.
- W3198419977 hasRelatedWork W2398548332 @default.
- W3198419977 hasRelatedWork W2757988102 @default.
- W3198419977 hasRelatedWork W2884815824 @default.
- W3198419977 hasRelatedWork W3120848961 @default.
- W3198419977 hasRelatedWork W4248269264 @default.
- W3198419977 hasRelatedWork W3135646670 @default.
- W3198419977 hasVolume "20" @default.
- W3198419977 isParatext "false" @default.
- W3198419977 isRetracted "false" @default.
- W3198419977 magId "3198419977" @default.
- W3198419977 workType "article" @default.