Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387428045> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4387428045 endingPage "336" @default.
- W4387428045 startingPage "325" @default.
- W4387428045 abstract "We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary limit of BERT, they only cover high-frequency words and fall back to character level when encountering out-of-vocabulary (OOV) words. Different from existing works, MarkBERT keeps the vocabulary being Chinese characters and inserts boundary markers between contiguous words. Such design enables the model to handle any words in the same way, no matter they are OOV words or not. Besides, our model has two additional benefits: first, it is convenient to add word-level learning objectives over markers, which is complementary to traditional character and sentence-level pretraining tasks; second, it can easily incorporate richer semantics such as POS tags of words by replacing generic markers with POS tag-specific markers. With the simple markers insertion, MarkBERT can improve the performances of various downstream tasks including language understanding and sequence labeling. (All the codes and models will be made publicly available at https://github.com/ )." @default.
- W4387428045 created "2023-10-08" @default.
- W4387428045 creator A5044029236 @default.
- W4387428045 creator A5044665993 @default.
- W4387428045 creator A5048168090 @default.
- W4387428045 creator A5052842216 @default.
- W4387428045 creator A5086682667 @default.
- W4387428045 creator A5087920747 @default.
- W4387428045 date "2023-01-01" @default.
- W4387428045 modified "2023-10-09" @default.
- W4387428045 title "MarkBERT: Marking Word Boundaries Improves Chinese BERT" @default.
- W4387428045 cites W2131988669 @default.
- W4387428045 cites W2962904552 @default.
- W4387428045 cites W3034379414 @default.
- W4387428045 cites W3035642486 @default.
- W4387428045 cites W3102725307 @default.
- W4387428045 cites W3106031450 @default.
- W4387428045 cites W3167136668 @default.
- W4387428045 cites W3170962005 @default.
- W4387428045 cites W3174396451 @default.
- W4387428045 cites W3176692111 @default.
- W4387428045 cites W3177365697 @default.
- W4387428045 doi "https://doi.org/10.1007/978-3-031-44693-1_26" @default.
- W4387428045 hasPublicationYear "2023" @default.
- W4387428045 type Work @default.
- W4387428045 citedByCount "0" @default.
- W4387428045 crossrefType "book-chapter" @default.
- W4387428045 hasAuthorship W4387428045A5044029236 @default.
- W4387428045 hasAuthorship W4387428045A5044665993 @default.
- W4387428045 hasAuthorship W4387428045A5048168090 @default.
- W4387428045 hasAuthorship W4387428045A5052842216 @default.
- W4387428045 hasAuthorship W4387428045A5086682667 @default.
- W4387428045 hasAuthorship W4387428045A5087920747 @default.
- W4387428045 hasConcept C138885662 @default.
- W4387428045 hasConcept C154945302 @default.
- W4387428045 hasConcept C184337299 @default.
- W4387428045 hasConcept C199360897 @default.
- W4387428045 hasConcept C204321447 @default.
- W4387428045 hasConcept C2524010 @default.
- W4387428045 hasConcept C2777530160 @default.
- W4387428045 hasConcept C2777601683 @default.
- W4387428045 hasConcept C2780861071 @default.
- W4387428045 hasConcept C28490314 @default.
- W4387428045 hasConcept C33923547 @default.
- W4387428045 hasConcept C41008148 @default.
- W4387428045 hasConcept C41895202 @default.
- W4387428045 hasConcept C90805587 @default.
- W4387428045 hasConceptScore W4387428045C138885662 @default.
- W4387428045 hasConceptScore W4387428045C154945302 @default.
- W4387428045 hasConceptScore W4387428045C184337299 @default.
- W4387428045 hasConceptScore W4387428045C199360897 @default.
- W4387428045 hasConceptScore W4387428045C204321447 @default.
- W4387428045 hasConceptScore W4387428045C2524010 @default.
- W4387428045 hasConceptScore W4387428045C2777530160 @default.
- W4387428045 hasConceptScore W4387428045C2777601683 @default.
- W4387428045 hasConceptScore W4387428045C2780861071 @default.
- W4387428045 hasConceptScore W4387428045C28490314 @default.
- W4387428045 hasConceptScore W4387428045C33923547 @default.
- W4387428045 hasConceptScore W4387428045C41008148 @default.
- W4387428045 hasConceptScore W4387428045C41895202 @default.
- W4387428045 hasConceptScore W4387428045C90805587 @default.
- W4387428045 hasLocation W43874280451 @default.
- W4387428045 hasOpenAccess W4387428045 @default.
- W4387428045 hasPrimaryLocation W43874280451 @default.
- W4387428045 hasRelatedWork W1503216044 @default.
- W4387428045 hasRelatedWork W1997182898 @default.
- W4387428045 hasRelatedWork W2347884623 @default.
- W4387428045 hasRelatedWork W2353650902 @default.
- W4387428045 hasRelatedWork W2354143083 @default.
- W4387428045 hasRelatedWork W2366269494 @default.
- W4387428045 hasRelatedWork W2369369044 @default.
- W4387428045 hasRelatedWork W2372906645 @default.
- W4387428045 hasRelatedWork W2393609567 @default.
- W4387428045 hasRelatedWork W4319998713 @default.
- W4387428045 isParatext "false" @default.
- W4387428045 isRetracted "false" @default.
- W4387428045 workType "book-chapter" @default.