Matches in SemOpenAlex for { <https://semopenalex.org/work/W2096438711> ?p ?o ?g. }
- W2096438711 endingPage "76" @default.
- W2096438711 startingPage "71" @default.
- W2096438711 abstract "Most text message normalization approaches are based on supervised learning and rely on human labeled training data. In addition, the nonstandard words are often categorized into different types and specific models are designed to tackle each type. In this paper, we propose a unified letter transformation approach that requires neither pre-categorization nor human supervision. Our approach models the generation process from the dictionary words to nonstandard tokens under a sequence labeling framework, where each letter in the dictionary word can be retained, removed, or substituted by other letters/digits. To avoid the expensive and time consuming hand labeling process, we automatically collected a large set of noisy training pairs using a novel web-based approach and performed character-level alignment for model training. Experiments on both Twitter and SMS messages show that our system significantly outperformed the state-of-the-art deletion-based abbreviation system and the jazzy spell checker (absolute accuracy gain of 21.69% and 18.16% over jazzy spell checker on the two test sets respectively)." @default.
- W2096438711 created "2016-06-24" @default.
- W2096438711 creator A5006239789 @default.
- W2096438711 creator A5023363049 @default.
- W2096438711 creator A5048279362 @default.
- W2096438711 creator A5061335554 @default.
- W2096438711 date "2011-06-19" @default.
- W2096438711 modified "2023-09-24" @default.
- W2096438711 title "Insertion, Deletion, or Substitution? Normalizing Text Messages without Pre-categorization nor Supervision" @default.
- W2096438711 cites W1533946607 @default.
- W2096438711 cites W1800296434 @default.
- W2096438711 cites W1976214863 @default.
- W2096438711 cites W2000877723 @default.
- W2096438711 cites W2050255038 @default.
- W2096438711 cites W2053966956 @default.
- W2096438711 cites W2101200183 @default.
- W2096438711 cites W2118947254 @default.
- W2096438711 cites W2133503566 @default.
- W2096438711 cites W2144226312 @default.
- W2096438711 cites W2147880316 @default.
- W2096438711 cites W2160637503 @default.
- W2096438711 cites W2163942301 @default.
- W2096438711 cites W2164107060 @default.
- W2096438711 hasPublicationYear "2011" @default.
- W2096438711 type Work @default.
- W2096438711 sameAs 2096438711 @default.
- W2096438711 citedByCount "70" @default.
- W2096438711 countsByYear W20964387112012 @default.
- W2096438711 countsByYear W20964387112013 @default.
- W2096438711 countsByYear W20964387112014 @default.
- W2096438711 countsByYear W20964387112015 @default.
- W2096438711 countsByYear W20964387112016 @default.
- W2096438711 countsByYear W20964387112017 @default.
- W2096438711 countsByYear W20964387112018 @default.
- W2096438711 countsByYear W20964387112019 @default.
- W2096438711 countsByYear W20964387112020 @default.
- W2096438711 countsByYear W20964387112021 @default.
- W2096438711 crossrefType "proceedings-article" @default.
- W2096438711 hasAuthorship W2096438711A5006239789 @default.
- W2096438711 hasAuthorship W2096438711A5023363049 @default.
- W2096438711 hasAuthorship W2096438711A5048279362 @default.
- W2096438711 hasAuthorship W2096438711A5061335554 @default.
- W2096438711 hasConcept C136886441 @default.
- W2096438711 hasConcept C138885662 @default.
- W2096438711 hasConcept C144024400 @default.
- W2096438711 hasConcept C154945302 @default.
- W2096438711 hasConcept C162324750 @default.
- W2096438711 hasConcept C169903167 @default.
- W2096438711 hasConcept C177264268 @default.
- W2096438711 hasConcept C187736073 @default.
- W2096438711 hasConcept C19165224 @default.
- W2096438711 hasConcept C199360897 @default.
- W2096438711 hasConcept C204321447 @default.
- W2096438711 hasConcept C2778220771 @default.
- W2096438711 hasConcept C2780451532 @default.
- W2096438711 hasConcept C2780957641 @default.
- W2096438711 hasConcept C28490314 @default.
- W2096438711 hasConcept C2986744138 @default.
- W2096438711 hasConcept C35639132 @default.
- W2096438711 hasConcept C41008148 @default.
- W2096438711 hasConcept C41895202 @default.
- W2096438711 hasConcept C51632099 @default.
- W2096438711 hasConcept C90805587 @default.
- W2096438711 hasConcept C94124525 @default.
- W2096438711 hasConceptScore W2096438711C136886441 @default.
- W2096438711 hasConceptScore W2096438711C138885662 @default.
- W2096438711 hasConceptScore W2096438711C144024400 @default.
- W2096438711 hasConceptScore W2096438711C154945302 @default.
- W2096438711 hasConceptScore W2096438711C162324750 @default.
- W2096438711 hasConceptScore W2096438711C169903167 @default.
- W2096438711 hasConceptScore W2096438711C177264268 @default.
- W2096438711 hasConceptScore W2096438711C187736073 @default.
- W2096438711 hasConceptScore W2096438711C19165224 @default.
- W2096438711 hasConceptScore W2096438711C199360897 @default.
- W2096438711 hasConceptScore W2096438711C204321447 @default.
- W2096438711 hasConceptScore W2096438711C2778220771 @default.
- W2096438711 hasConceptScore W2096438711C2780451532 @default.
- W2096438711 hasConceptScore W2096438711C2780957641 @default.
- W2096438711 hasConceptScore W2096438711C28490314 @default.
- W2096438711 hasConceptScore W2096438711C2986744138 @default.
- W2096438711 hasConceptScore W2096438711C35639132 @default.
- W2096438711 hasConceptScore W2096438711C41008148 @default.
- W2096438711 hasConceptScore W2096438711C41895202 @default.
- W2096438711 hasConceptScore W2096438711C51632099 @default.
- W2096438711 hasConceptScore W2096438711C90805587 @default.
- W2096438711 hasConceptScore W2096438711C94124525 @default.
- W2096438711 hasLocation W20964387111 @default.
- W2096438711 hasOpenAccess W2096438711 @default.
- W2096438711 hasPrimaryLocation W20964387111 @default.
- W2096438711 hasRelatedWork W157541337 @default.
- W2096438711 hasRelatedWork W1868971014 @default.
- W2096438711 hasRelatedWork W1976214863 @default.
- W2096438711 hasRelatedWork W2016443085 @default.
- W2096438711 hasRelatedWork W2053966956 @default.
- W2096438711 hasRelatedWork W2057900969 @default.
- W2096438711 hasRelatedWork W2101200183 @default.
- W2096438711 hasRelatedWork W2112255502 @default.
- W2096438711 hasRelatedWork W2133503566 @default.