Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298616685> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4298616685 abstract "Abstract In mobile communications, plenty of textual messages need to be transmitted and processed rapidly. However, messages usually contain noise, which will affect the performance of related applications. Thus, we investigate grammatical error correction (GEC) to correct errors in messages. Unlike recent works, we focus on improving the efficiency of GEC because low time delay is significant in mobile communications. We propose a novel multi-task learning approach to GEC by detecting errors first and then making corrections. Two classifiers are used to serially detect sentence-level and token-level errors, so the correct content can be free from correction operations. We adapt a non-autoregressive decoder to parallelly generate corrected tokens, making the correction stage efficient. Experiments show that our approach is ten times faster than the traditional approach and can achieve a comparable GEC performance." @default.
- W4298616685 created "2022-10-02" @default.
- W4298616685 creator A5028942172 @default.
- W4298616685 creator A5052160218 @default.
- W4298616685 creator A5068538399 @default.
- W4298616685 date "2022-10-01" @default.
- W4298616685 modified "2023-09-30" @default.
- W4298616685 title "A multi-task learning framework for efficient grammatical error correction of textual messages in mobile communications" @default.
- W4298616685 cites W2098297786 @default.
- W4298616685 cites W2251418581 @default.
- W4298616685 cites W2470324779 @default.
- W4298616685 cites W2478432301 @default.
- W4298616685 cites W2741494657 @default.
- W4298616685 cites W2798416860 @default.
- W4298616685 cites W2948335087 @default.
- W4298616685 cites W2953083125 @default.
- W4298616685 cites W2963341956 @default.
- W4298616685 cites W2963881719 @default.
- W4298616685 cites W2964082031 @default.
- W4298616685 cites W2970294904 @default.
- W4298616685 cites W2970429618 @default.
- W4298616685 cites W2970744242 @default.
- W4298616685 cites W2970868759 @default.
- W4298616685 cites W3011411500 @default.
- W4298616685 cites W3035010485 @default.
- W4298616685 cites W3037162118 @default.
- W4298616685 cites W3089727447 @default.
- W4298616685 cites W3105306115 @default.
- W4298616685 cites W3107486494 @default.
- W4298616685 cites W3175441946 @default.
- W4298616685 cites W3213344990 @default.
- W4298616685 cites W3217000788 @default.
- W4298616685 cites W4225526013 @default.
- W4298616685 cites W4285130686 @default.
- W4298616685 cites W4302218341 @default.
- W4298616685 doi "https://doi.org/10.1186/s13638-022-02182-8" @default.
- W4298616685 hasPublicationYear "2022" @default.
- W4298616685 type Work @default.
- W4298616685 citedByCount "0" @default.
- W4298616685 crossrefType "journal-article" @default.
- W4298616685 hasAuthorship W4298616685A5028942172 @default.
- W4298616685 hasAuthorship W4298616685A5052160218 @default.
- W4298616685 hasAuthorship W4298616685A5068538399 @default.
- W4298616685 hasBestOaLocation W42986166851 @default.
- W4298616685 hasConcept C103088060 @default.
- W4298616685 hasConcept C11413529 @default.
- W4298616685 hasConcept C120665830 @default.
- W4298616685 hasConcept C121332964 @default.
- W4298616685 hasConcept C154945302 @default.
- W4298616685 hasConcept C162324750 @default.
- W4298616685 hasConcept C187736073 @default.
- W4298616685 hasConcept C192209626 @default.
- W4298616685 hasConcept C204321447 @default.
- W4298616685 hasConcept C2777530160 @default.
- W4298616685 hasConcept C2780451532 @default.
- W4298616685 hasConcept C28490314 @default.
- W4298616685 hasConcept C31258907 @default.
- W4298616685 hasConcept C41008148 @default.
- W4298616685 hasConcept C48145219 @default.
- W4298616685 hasConceptScore W4298616685C103088060 @default.
- W4298616685 hasConceptScore W4298616685C11413529 @default.
- W4298616685 hasConceptScore W4298616685C120665830 @default.
- W4298616685 hasConceptScore W4298616685C121332964 @default.
- W4298616685 hasConceptScore W4298616685C154945302 @default.
- W4298616685 hasConceptScore W4298616685C162324750 @default.
- W4298616685 hasConceptScore W4298616685C187736073 @default.
- W4298616685 hasConceptScore W4298616685C192209626 @default.
- W4298616685 hasConceptScore W4298616685C204321447 @default.
- W4298616685 hasConceptScore W4298616685C2777530160 @default.
- W4298616685 hasConceptScore W4298616685C2780451532 @default.
- W4298616685 hasConceptScore W4298616685C28490314 @default.
- W4298616685 hasConceptScore W4298616685C31258907 @default.
- W4298616685 hasConceptScore W4298616685C41008148 @default.
- W4298616685 hasConceptScore W4298616685C48145219 @default.
- W4298616685 hasIssue "1" @default.
- W4298616685 hasLocation W42986166851 @default.
- W4298616685 hasOpenAccess W4298616685 @default.
- W4298616685 hasPrimaryLocation W42986166851 @default.
- W4298616685 hasRelatedWork W1492132281 @default.
- W4298616685 hasRelatedWork W1573537589 @default.
- W4298616685 hasRelatedWork W159132833 @default.
- W4298616685 hasRelatedWork W2375389409 @default.
- W4298616685 hasRelatedWork W3082447286 @default.
- W4298616685 hasRelatedWork W3184514313 @default.
- W4298616685 hasRelatedWork W3213808804 @default.
- W4298616685 hasRelatedWork W4221165884 @default.
- W4298616685 hasRelatedWork W4323341682 @default.
- W4298616685 hasRelatedWork W4386784623 @default.
- W4298616685 hasVolume "2022" @default.
- W4298616685 isParatext "false" @default.
- W4298616685 isRetracted "false" @default.
- W4298616685 workType "article" @default.