Matches in SemOpenAlex for { <https://semopenalex.org/work/W2168776871> ?p ?o ?g. }
- W2168776871 endingPage "351" @default.
- W2168776871 startingPage "344" @default.
- W2168776871 abstract "In evaluating the output of language technology applications—MT, natural language generation, summarisation—automatic evaluation techniques generally conflate measurement of faithfulness to source content with fluency of the resulting text. In this paper we develop an automatic evaluation metric to estimate fluency alone, by examining the use of parser outputs as metrics, and show that they correlate with human judgements of generated text fluency. We then develop a machine learner based on these, and show that this performs better than the individual parser metrics, approaching a lower bound on human performance. We finally look at different language models for generating sentences, and show that while individual parser metrics can be ‘fooled’ depending on generation method, the machine learner provides a consistent estimator of fluency." @default.
- W2168776871 created "2016-06-24" @default.
- W2168776871 creator A5008748003 @default.
- W2168776871 creator A5022216838 @default.
- W2168776871 creator A5058355406 @default.
- W2168776871 creator A5076667934 @default.
- W2168776871 date "2007-06-01" @default.
- W2168776871 modified "2023-09-23" @default.
- W2168776871 title "GLEU: Automatic Evaluation of Sentence-Level Fluency" @default.
- W2168776871 cites W1489409710 @default.
- W2168776871 cites W1489525520 @default.
- W2168776871 cites W1493882948 @default.
- W2168776871 cites W1528941926 @default.
- W2168776871 cites W1544826511 @default.
- W2168776871 cites W1576520375 @default.
- W2168776871 cites W1579838312 @default.
- W2168776871 cites W1657362120 @default.
- W2168776871 cites W1991158387 @default.
- W2168776871 cites W2068390867 @default.
- W2168776871 cites W2081035377 @default.
- W2168776871 cites W2092654472 @default.
- W2168776871 cites W2101105183 @default.
- W2168776871 cites W2107031757 @default.
- W2168776871 cites W2134492274 @default.
- W2168776871 cites W2466204975 @default.
- W2168776871 hasPublicationYear "2007" @default.
- W2168776871 type Work @default.
- W2168776871 sameAs 2168776871 @default.
- W2168776871 citedByCount "28" @default.
- W2168776871 countsByYear W21687768712012 @default.
- W2168776871 countsByYear W21687768712013 @default.
- W2168776871 countsByYear W21687768712014 @default.
- W2168776871 countsByYear W21687768712015 @default.
- W2168776871 countsByYear W21687768712016 @default.
- W2168776871 countsByYear W21687768712018 @default.
- W2168776871 countsByYear W21687768712021 @default.
- W2168776871 crossrefType "proceedings-article" @default.
- W2168776871 hasAuthorship W2168776871A5008748003 @default.
- W2168776871 hasAuthorship W2168776871A5022216838 @default.
- W2168776871 hasAuthorship W2168776871A5058355406 @default.
- W2168776871 hasAuthorship W2168776871A5076667934 @default.
- W2168776871 hasConcept C105795698 @default.
- W2168776871 hasConcept C130440534 @default.
- W2168776871 hasConcept C138885662 @default.
- W2168776871 hasConcept C154945302 @default.
- W2168776871 hasConcept C162324750 @default.
- W2168776871 hasConcept C176217482 @default.
- W2168776871 hasConcept C185429906 @default.
- W2168776871 hasConcept C186644900 @default.
- W2168776871 hasConcept C195324797 @default.
- W2168776871 hasConcept C204321447 @default.
- W2168776871 hasConcept C21547014 @default.
- W2168776871 hasConcept C2776187449 @default.
- W2168776871 hasConcept C2777413886 @default.
- W2168776871 hasConcept C2777530160 @default.
- W2168776871 hasConcept C28490314 @default.
- W2168776871 hasConcept C33923547 @default.
- W2168776871 hasConcept C41008148 @default.
- W2168776871 hasConcept C41895202 @default.
- W2168776871 hasConceptScore W2168776871C105795698 @default.
- W2168776871 hasConceptScore W2168776871C130440534 @default.
- W2168776871 hasConceptScore W2168776871C138885662 @default.
- W2168776871 hasConceptScore W2168776871C154945302 @default.
- W2168776871 hasConceptScore W2168776871C162324750 @default.
- W2168776871 hasConceptScore W2168776871C176217482 @default.
- W2168776871 hasConceptScore W2168776871C185429906 @default.
- W2168776871 hasConceptScore W2168776871C186644900 @default.
- W2168776871 hasConceptScore W2168776871C195324797 @default.
- W2168776871 hasConceptScore W2168776871C204321447 @default.
- W2168776871 hasConceptScore W2168776871C21547014 @default.
- W2168776871 hasConceptScore W2168776871C2776187449 @default.
- W2168776871 hasConceptScore W2168776871C2777413886 @default.
- W2168776871 hasConceptScore W2168776871C2777530160 @default.
- W2168776871 hasConceptScore W2168776871C28490314 @default.
- W2168776871 hasConceptScore W2168776871C33923547 @default.
- W2168776871 hasConceptScore W2168776871C41008148 @default.
- W2168776871 hasConceptScore W2168776871C41895202 @default.
- W2168776871 hasLocation W21687768711 @default.
- W2168776871 hasOpenAccess W2168776871 @default.
- W2168776871 hasPrimaryLocation W21687768711 @default.
- W2168776871 hasRelatedWork W136568931 @default.
- W2168776871 hasRelatedWork W1534218608 @default.
- W2168776871 hasRelatedWork W1535015163 @default.
- W2168776871 hasRelatedWork W1631260214 @default.
- W2168776871 hasRelatedWork W1967390364 @default.
- W2168776871 hasRelatedWork W2019416425 @default.
- W2168776871 hasRelatedWork W2041826927 @default.
- W2168776871 hasRelatedWork W2067608147 @default.
- W2168776871 hasRelatedWork W2068390867 @default.
- W2168776871 hasRelatedWork W2097606805 @default.
- W2168776871 hasRelatedWork W2101105183 @default.
- W2168776871 hasRelatedWork W2125712079 @default.
- W2168776871 hasRelatedWork W2126920742 @default.
- W2168776871 hasRelatedWork W2140676672 @default.
- W2168776871 hasRelatedWork W2154652894 @default.
- W2168776871 hasRelatedWork W2162211144 @default.
- W2168776871 hasRelatedWork W2167193140 @default.
- W2168776871 hasRelatedWork W2169546346 @default.