FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2976042047> ?p ?o ?g. }

• W2976042047 abstract "Recently, pre-trained language models have achieved remarkable success in a broad range of natural language processing tasks. However, in multilingual setting, it is extremely resource-consuming to pre-train a deep language model over large-scale corpora for each language. Instead of exhaustively pre-training monolingual language models independently, an alternative solution is to pre-train a powerful multilingual deep language model over large-scale corpora in hundreds of languages. However, the vocabulary size for each language in such a model is relatively small, especially for low-resource languages. This limitation inevitably hinders the performance of these multilingual models on tasks such as sequence labeling, wherein in-depth token-level or sentence-level understanding is essential. In this paper, inspired by previous methods designed for monolingual settings, we investigate two approaches (i.e., joint mapping and mixture mapping) based on a pre-trained multilingual model BERT for addressing the out-of-vocabulary (OOV) problem on a variety of tasks, including part-of-speech tagging, named entity recognition, machine translation quality estimation, and machine reading comprehension. Experimental results show that using mixture mapping is more promising. To the best of our knowledge, this is the first work that attempts to address and discuss the OOV issue in multilingual settings." @default.
• W2976042047 created "2019-10-03" @default.
• W2976042047 creator A5034476404 @default.
• W2976042047 creator A5036397366 @default.
• W2976042047 creator A5053739372 @default.
• W2976042047 creator A5060766913 @default.
• W2976042047 creator A5063784915 @default.
• W2976042047 date "2019-09-26" @default.
• W2976042047 modified "2023-09-25" @default.
• W2976042047 title "Improving Pre-Trained Multilingual Models with Vocabulary Expansion" @default.
• W2976042047 cites W1523385540 @default.
• W2976042047 cites W1544827683 @default.
• W2976042047 cites W1566289585 @default.
• W2976042047 cites W1899794420 @default.
• W2976042047 cites W1938755728 @default.
• W2976042047 cites W2100664567 @default.
• W2976042047 cites W2101609803 @default.
• W2976042047 cites W2118090838 @default.
• W2976042047 cites W2118434577 @default.
• W2976042047 cites W2147880316 @default.
• W2976042047 cites W2153579005 @default.
• W2976042047 cites W2172699681 @default.
• W2976042047 cites W2176637712 @default.
• W2976042047 cites W2220350356 @default.
• W2976042047 cites W2250491963 @default.
• W2976042047 cites W2250709962 @default.
• W2976042047 cites W2251302843 @default.
• W2976042047 cites W2262099980 @default.
• W2976042047 cites W2294774419 @default.
• W2976042047 cites W2295584157 @default.
• W2976042047 cites W2311921240 @default.
• W2976042047 cites W2493916176 @default.
• W2976042047 cites W2525778437 @default.
• W2976042047 cites W2577335011 @default.
• W2976042047 cites W2578569244 @default.
• W2976042047 cites W2621404689 @default.
• W2976042047 cites W2727973045 @default.
• W2976042047 cites W2739533097 @default.
• W2976042047 cites W2751916302 @default.
• W2976042047 cites W2758123554 @default.
• W2976042047 cites W2759366113 @default.
• W2976042047 cites W2767321762 @default.
• W2976042047 cites W2798931235 @default.
• W2976042047 cites W2803484822 @default.
• W2976042047 cites W2807036468 @default.
• W2976042047 cites W2835793135 @default.
• W2976042047 cites W2883775990 @default.
• W2976042047 cites W2884519246 @default.
• W2976042047 cites W2888456631 @default.
• W2976042047 cites W2890244613 @default.
• W2976042047 cites W2896457183 @default.
• W2976042047 cites W2902463012 @default.
• W2976042047 cites W2903193068 @default.
• W2976042047 cites W2949548130 @default.
• W2976042047 cites W2951976932 @default.
• W2976042047 cites W2962699518 @default.
• W2976042047 cites W2962739339 @default.
• W2976042047 cites W2962784628 @default.
• W2976042047 cites W2963012544 @default.
• W2976042047 cites W2963045354 @default.
• W2976042047 cites W2963047628 @default.
• W2976042047 cites W2963052942 @default.
• W2976042047 cites W2963118869 @default.
• W2976042047 cites W2963208801 @default.
• W2976042047 cites W2963324947 @default.
• W2976042047 cites W2963347649 @default.
• W2976042047 cites W2963421945 @default.
• W2976042047 cites W2963472233 @default.
• W2976042047 cites W2963547384 @default.
• W2976042047 cites W2963563735 @default.
• W2976042047 cites W2963682821 @default.
• W2976042047 cites W2963800216 @default.
• W2976042047 cites W2963917673 @default.
• W2976042047 cites W2963925965 @default.
• W2976042047 cites W2963993537 @default.
• W2976042047 cites W2964090065 @default.
• W2976042047 cites W2964246695 @default.
• W2976042047 cites W2964296073 @default.
• W2976042047 cites W2964302308 @default.
• W2976042047 cites W331019419 @default.
• W2976042047 cites W342285082 @default.
• W2976042047 hasPublicationYear "2019" @default.
• W2976042047 type Work @default.
• W2976042047 sameAs 2976042047 @default.
• W2976042047 citedByCount "1" @default.
• W2976042047 countsByYear W29760420472019 @default.
• W2976042047 crossrefType "posted-content" @default.
• W2976042047 hasAuthorship W2976042047A5034476404 @default.
• W2976042047 hasAuthorship W2976042047A5036397366 @default.
• W2976042047 hasAuthorship W2976042047A5053739372 @default.
• W2976042047 hasAuthorship W2976042047A5060766913 @default.
• W2976042047 hasAuthorship W2976042047A5063784915 @default.
• W2976042047 hasConcept C136197465 @default.
• W2976042047 hasConcept C137293760 @default.
• W2976042047 hasConcept C138885662 @default.
• W2976042047 hasConcept C154945302 @default.
• W2976042047 hasConcept C203005215 @default.
• W2976042047 hasConcept C204321447 @default.
• W2976042047 hasConcept C206345919 @default.
• W2976042047 hasConcept C2777530160 @default.

• next