Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126173663> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W3126173663 abstract "Intended for reducing manual inspection costs and semantic misunderstandings, Chinese Spelling Check (CSC) has been investigated extensively in natural language processing. However, little work has yet been done on input-method-based CSC in which CSC can make use of Pinyin information to improve spelling correction efficiency. This paper proposes a novel CSC architecture, IME-Spell, based on pre-trained context vectors for input methods, which consists of two parts as follows. The Chinese spelling detection part of the architecture adopts the fusion vectors of character-based pre-trained context vectors and Pinyin vectors, and uses the method of sequence labeling to detect the error characters. The Chinese spelling correction part of the architecture adopts Masked Language Model (MLM) to generate a candidate set of erroneous characters, and uses XGBoost and Pinyin-to-Character conversion models to filter correct characters and correct the error characters for users. IME-Spell has a significant improvement over the benchmark models on the SIGHAN dataset, whose maximum difference of F1 in the spelling detection and correction subtasks reach 48.9% and 27.8%, respectively." @default.
- W3126173663 created "2021-02-15" @default.
- W3126173663 creator A5018045825 @default.
- W3126173663 creator A5018873816 @default.
- W3126173663 creator A5089504286 @default.
- W3126173663 date "2020-12-18" @default.
- W3126173663 modified "2023-09-24" @default.
- W3126173663 title "IME-Spell" @default.
- W3126173663 cites W1934041838 @default.
- W3126173663 cites W1991133427 @default.
- W3126173663 cites W2158195707 @default.
- W3126173663 cites W2892311186 @default.
- W3126173663 doi "https://doi.org/10.1145/3443279.3443297" @default.
- W3126173663 hasPublicationYear "2020" @default.
- W3126173663 type Work @default.
- W3126173663 sameAs 3126173663 @default.
- W3126173663 citedByCount "1" @default.
- W3126173663 countsByYear W31261736632023 @default.
- W3126173663 crossrefType "proceedings-article" @default.
- W3126173663 hasAuthorship W3126173663A5018045825 @default.
- W3126173663 hasAuthorship W3126173663A5018873816 @default.
- W3126173663 hasAuthorship W3126173663A5089504286 @default.
- W3126173663 hasConcept C138885662 @default.
- W3126173663 hasConcept C27206212 @default.
- W3126173663 hasConcept C2780957641 @default.
- W3126173663 hasConcept C41008148 @default.
- W3126173663 hasConceptScore W3126173663C138885662 @default.
- W3126173663 hasConceptScore W3126173663C27206212 @default.
- W3126173663 hasConceptScore W3126173663C2780957641 @default.
- W3126173663 hasConceptScore W3126173663C41008148 @default.
- W3126173663 hasLocation W31261736631 @default.
- W3126173663 hasOpenAccess W3126173663 @default.
- W3126173663 hasPrimaryLocation W31261736631 @default.
- W3126173663 hasRelatedWork W1715012949 @default.
- W3126173663 hasRelatedWork W2000570511 @default.
- W3126173663 hasRelatedWork W2030161905 @default.
- W3126173663 hasRelatedWork W2745258745 @default.
- W3126173663 hasRelatedWork W2748952813 @default.
- W3126173663 hasRelatedWork W2899084033 @default.
- W3126173663 hasRelatedWork W4287201819 @default.
- W3126173663 hasRelatedWork W4287256643 @default.
- W3126173663 hasRelatedWork W4296626305 @default.
- W3126173663 hasRelatedWork W4307454463 @default.
- W3126173663 isParatext "false" @default.
- W3126173663 isRetracted "false" @default.
- W3126173663 magId "3126173663" @default.
- W3126173663 workType "article" @default.