Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034272764> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3034272764 abstract "In many languages like Arabic, diacritics are used to specify pronunciations as well as meanings. Such diacritics are often omitted in written text, increasing the number of possible pronunciations and meanings for a word. This results in a more ambiguous text making computational processing on such text more difficult. Diacritic restoration is the task of restoring missing diacritics in the written text. Most state-of-the-art diacritic restoration models are built on character level information which helps generalize the model to unseen data, but presumably lose useful information at the word level. Thus, to compensate for this loss, we investigate the use of multi-task learning to jointly optimize diacritic restoration with related NLP problems namely word segmentation, part-of-speech tagging, and syntactic diacritization. We use Arabic as a case study since it has sufficient data resources for tasks that we consider in our joint modeling. Our joint models significantly outperform the baselines and are comparable to the state-of-the-art models that are more complex relying on morphological analyzers and/or a lot more data (e.g. dialectal data)." @default.
- W3034272764 created "2020-06-19" @default.
- W3034272764 creator A5038581447 @default.
- W3034272764 creator A5051917159 @default.
- W3034272764 creator A5065997880 @default.
- W3034272764 date "2020-01-01" @default.
- W3034272764 modified "2023-09-23" @default.
- W3034272764 title "A Multitask Learning Approach for Diacritic Restoration" @default.
- W3034272764 cites W125610139 @default.
- W3034272764 cites W1553623403 @default.
- W3034272764 cites W1598638450 @default.
- W3034272764 cites W2011402185 @default.
- W3034272764 cites W2041375131 @default.
- W3034272764 cites W2048978997 @default.
- W3034272764 cites W2056382745 @default.
- W3034272764 cites W2064675550 @default.
- W3034272764 cites W2065400286 @default.
- W3034272764 cites W2067861964 @default.
- W3034272764 cites W2131774270 @default.
- W3034272764 cites W2153186553 @default.
- W3034272764 cites W2250509225 @default.
- W3034272764 cites W2250816155 @default.
- W3034272764 cites W2493916176 @default.
- W3034272764 cites W2556468274 @default.
- W3034272764 cites W2740272870 @default.
- W3034272764 cites W2740870334 @default.
- W3034272764 cites W2757376562 @default.
- W3034272764 cites W2795877110 @default.
- W3034272764 cites W2798935874 @default.
- W3034272764 cites W2885738119 @default.
- W3034272764 cites W2890328620 @default.
- W3034272764 cites W2963677766 @default.
- W3034272764 cites W3008803645 @default.
- W3034272764 cites W3202110839 @default.
- W3034272764 doi "https://doi.org/10.18653/v1/2020.acl-main.732" @default.
- W3034272764 hasPublicationYear "2020" @default.
- W3034272764 type Work @default.
- W3034272764 sameAs 3034272764 @default.
- W3034272764 citedByCount "8" @default.
- W3034272764 countsByYear W30342727642021 @default.
- W3034272764 countsByYear W30342727642022 @default.
- W3034272764 countsByYear W30342727642023 @default.
- W3034272764 crossrefType "proceedings-article" @default.
- W3034272764 hasAuthorship W3034272764A5038581447 @default.
- W3034272764 hasAuthorship W3034272764A5051917159 @default.
- W3034272764 hasAuthorship W3034272764A5065997880 @default.
- W3034272764 hasBestOaLocation W30342727642 @default.
- W3034272764 hasConcept C127413603 @default.
- W3034272764 hasConcept C154945302 @default.
- W3034272764 hasConcept C201995342 @default.
- W3034272764 hasConcept C2780451532 @default.
- W3034272764 hasConcept C28006648 @default.
- W3034272764 hasConcept C41008148 @default.
- W3034272764 hasConceptScore W3034272764C127413603 @default.
- W3034272764 hasConceptScore W3034272764C154945302 @default.
- W3034272764 hasConceptScore W3034272764C201995342 @default.
- W3034272764 hasConceptScore W3034272764C2780451532 @default.
- W3034272764 hasConceptScore W3034272764C28006648 @default.
- W3034272764 hasConceptScore W3034272764C41008148 @default.
- W3034272764 hasLocation W30342727641 @default.
- W3034272764 hasLocation W30342727642 @default.
- W3034272764 hasOpenAccess W3034272764 @default.
- W3034272764 hasPrimaryLocation W30342727641 @default.
- W3034272764 hasRelatedWork W1812322370 @default.
- W3034272764 hasRelatedWork W2337287714 @default.
- W3034272764 hasRelatedWork W2597787948 @default.
- W3034272764 hasRelatedWork W2790819610 @default.
- W3034272764 hasRelatedWork W2951786554 @default.
- W3034272764 hasRelatedWork W3031818154 @default.
- W3034272764 hasRelatedWork W3047894882 @default.
- W3034272764 hasRelatedWork W3095538999 @default.
- W3034272764 hasRelatedWork W3181335979 @default.
- W3034272764 hasRelatedWork W3200361725 @default.
- W3034272764 isParatext "false" @default.
- W3034272764 isRetracted "false" @default.
- W3034272764 magId "3034272764" @default.
- W3034272764 workType "article" @default.