FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2982063553> ?p ?o ?g. }

• W2982063553 abstract "Neural language models (LMs) have shown to benefit significantly from enhancing word vectors with subword-level information, especially for morphologically rich languages. This has been mainly tackled by providing subword-level information as an input; using subword units in the output layer has been far less explored. In this work, we propose LMs that are cognizant of the underlying stems in each word. We derive stems for words using a simple unsupervised technique for stem identification. We experiment with different architectures involving multi-task learning and mixture models over words and stems. We focus on four morphologically complex languages -- Hindi, Tamil, Kannada and Finnish -- and observe significant perplexity gains with using our stem-driven LMs when compared with other competitive baseline models." @default.
• W2982063553 created "2019-11-01" @default.
• W2982063553 creator A5007818678 @default.
• W2982063553 creator A5008761021 @default.
• W2982063553 creator A5036738038 @default.
• W2982063553 creator A5050514068 @default.
• W2982063553 date "2019-10-25" @default.
• W2982063553 modified "2023-09-27" @default.
• W2982063553 title "Stem-driven Language Models for Morphologically Rich Languages" @default.
• W2982063553 cites W1505680913 @default.
• W2982063553 cites W1938755728 @default.
• W2982063553 cites W2101711363 @default.
• W2982063553 cites W2148392518 @default.
• W2982063553 cites W2220350356 @default.
• W2982063553 cites W2251012068 @default.
• W2982063553 cites W2251150025 @default.
• W2982063553 cites W2296283641 @default.
• W2982063553 cites W2417763662 @default.
• W2982063553 cites W2472014052 @default.
• W2982063553 cites W2518150831 @default.
• W2982063553 cites W2564287196 @default.
• W2982063553 cites W2591264712 @default.
• W2982063553 cites W2611767671 @default.
• W2982063553 cites W2804639187 @default.
• W2982063553 cites W2883158411 @default.
• W2982063553 cites W2899771611 @default.
• W2982063553 cites W2949833739 @default.
• W2982063553 cites W2952097392 @default.
• W2982063553 cites W2962935543 @default.
• W2982063553 cites W2963537482 @default.
• W2982063553 cites W2963547384 @default.
• W2982063553 cites W2963824800 @default.
• W2982063553 hasPublicationYear "2019" @default.
• W2982063553 type Work @default.
• W2982063553 sameAs 2982063553 @default.
• W2982063553 citedByCount "0" @default.
• W2982063553 crossrefType "posted-content" @default.
• W2982063553 hasAuthorship W2982063553A5007818678 @default.
• W2982063553 hasAuthorship W2982063553A5008761021 @default.
• W2982063553 hasAuthorship W2982063553A5036738038 @default.
• W2982063553 hasAuthorship W2982063553A5050514068 @default.
• W2982063553 hasConcept C100279451 @default.
• W2982063553 hasConcept C111368507 @default.
• W2982063553 hasConcept C111472728 @default.
• W2982063553 hasConcept C120665830 @default.
• W2982063553 hasConcept C121332964 @default.
• W2982063553 hasConcept C12725497 @default.
• W2982063553 hasConcept C127313418 @default.
• W2982063553 hasConcept C137293760 @default.
• W2982063553 hasConcept C138885662 @default.
• W2982063553 hasConcept C140688305 @default.
• W2982063553 hasConcept C154945302 @default.
• W2982063553 hasConcept C162324750 @default.
• W2982063553 hasConcept C187736073 @default.
• W2982063553 hasConcept C192209626 @default.
• W2982063553 hasConcept C204321447 @default.
• W2982063553 hasConcept C2780451532 @default.
• W2982063553 hasConcept C2780586882 @default.
• W2982063553 hasConcept C41008148 @default.
• W2982063553 hasConcept C41895202 @default.
• W2982063553 hasConcept C519982507 @default.
• W2982063553 hasConcept C90805587 @default.
• W2982063553 hasConceptScore W2982063553C100279451 @default.
• W2982063553 hasConceptScore W2982063553C111368507 @default.
• W2982063553 hasConceptScore W2982063553C111472728 @default.
• W2982063553 hasConceptScore W2982063553C120665830 @default.
• W2982063553 hasConceptScore W2982063553C121332964 @default.
• W2982063553 hasConceptScore W2982063553C12725497 @default.
• W2982063553 hasConceptScore W2982063553C127313418 @default.
• W2982063553 hasConceptScore W2982063553C137293760 @default.
• W2982063553 hasConceptScore W2982063553C138885662 @default.
• W2982063553 hasConceptScore W2982063553C140688305 @default.
• W2982063553 hasConceptScore W2982063553C154945302 @default.
• W2982063553 hasConceptScore W2982063553C162324750 @default.
• W2982063553 hasConceptScore W2982063553C187736073 @default.
• W2982063553 hasConceptScore W2982063553C192209626 @default.
• W2982063553 hasConceptScore W2982063553C204321447 @default.
• W2982063553 hasConceptScore W2982063553C2780451532 @default.
• W2982063553 hasConceptScore W2982063553C2780586882 @default.
• W2982063553 hasConceptScore W2982063553C41008148 @default.
• W2982063553 hasConceptScore W2982063553C41895202 @default.
• W2982063553 hasConceptScore W2982063553C519982507 @default.
• W2982063553 hasConceptScore W2982063553C90805587 @default.
• W2982063553 hasLocation W29820635531 @default.
• W2982063553 hasOpenAccess W2982063553 @default.
• W2982063553 hasPrimaryLocation W29820635531 @default.
• W2982063553 hasRelatedWork W2250542250 @default.
• W2982063553 hasRelatedWork W2426917359 @default.
• W2982063553 hasRelatedWork W2759285320 @default.
• W2982063553 hasRelatedWork W2761001872 @default.
• W2982063553 hasRelatedWork W2790574369 @default.
• W2982063553 hasRelatedWork W2891068404 @default.
• W2982063553 hasRelatedWork W2941819978 @default.
• W2982063553 hasRelatedWork W2952094673 @default.
• W2982063553 hasRelatedWork W2968515498 @default.
• W2982063553 hasRelatedWork W2998337134 @default.
• W2982063553 hasRelatedWork W3029003064 @default.
• W2982063553 hasRelatedWork W3030402048 @default.
• W2982063553 hasRelatedWork W3082453117 @default.
• W2982063553 hasRelatedWork W3090672229 @default.

• next