Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891933988> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2891933988 endingPage "139" @default.
- W2891933988 startingPage "122" @default.
- W2891933988 abstract "This paper presents adversarial training and decoding methods for neural conversation models that can generate natural responses given dialog contexts. In our prior work, we built several end-to-end conversation systems for the 6th Dialog System Technology Challenges (DSTC6) Twitter help-desk dialog task. These systems included novel extensions of sequence adversarial training, example-based response extraction, and Minimum Bayes-Risk based system combination. In DSTC6, our systems achieved the best performance in most objective measures such as BLEU and METEOR scores and decent performance in a subjective measure based on human rating. In this paper, we provide a complete set of our experiments for DSTC6 and further extend the training and decoding strategies more focusing on improving the subjective measure, where we combine responses of three adversarial models. Experimental results demonstrate that the extended methods improve the human rating score and outperform the best score in DSTC6." @default.
- W2891933988 created "2018-09-27" @default.
- W2891933988 creator A5001601327 @default.
- W2891933988 creator A5049242358 @default.
- W2891933988 creator A5070802519 @default.
- W2891933988 creator A5072669943 @default.
- W2891933988 creator A5082524152 @default.
- W2891933988 creator A5087554069 @default.
- W2891933988 date "2019-03-01" @default.
- W2891933988 modified "2023-10-12" @default.
- W2891933988 title "Adversarial training and decoding strategies for end-to-end neural conversation models" @default.
- W2891933988 cites W1979299372 @default.
- W2891933988 cites W2119717200 @default.
- W2891933988 cites W2130607791 @default.
- W2891933988 cites W2160219061 @default.
- W2891933988 cites W2581637843 @default.
- W2891933988 cites W2601324753 @default.
- W2891933988 cites W2604178507 @default.
- W2891933988 cites W2962854379 @default.
- W2891933988 cites W2963206148 @default.
- W2891933988 cites W4211048027 @default.
- W2891933988 doi "https://doi.org/10.1016/j.csl.2018.08.006" @default.
- W2891933988 hasPublicationYear "2019" @default.
- W2891933988 type Work @default.
- W2891933988 sameAs 2891933988 @default.
- W2891933988 citedByCount "7" @default.
- W2891933988 countsByYear W28919339882019 @default.
- W2891933988 countsByYear W28919339882020 @default.
- W2891933988 countsByYear W28919339882021 @default.
- W2891933988 countsByYear W28919339882022 @default.
- W2891933988 crossrefType "journal-article" @default.
- W2891933988 hasAuthorship W2891933988A5001601327 @default.
- W2891933988 hasAuthorship W2891933988A5049242358 @default.
- W2891933988 hasAuthorship W2891933988A5070802519 @default.
- W2891933988 hasAuthorship W2891933988A5072669943 @default.
- W2891933988 hasAuthorship W2891933988A5082524152 @default.
- W2891933988 hasAuthorship W2891933988A5087554069 @default.
- W2891933988 hasConcept C11413529 @default.
- W2891933988 hasConcept C119857082 @default.
- W2891933988 hasConcept C124101348 @default.
- W2891933988 hasConcept C136764020 @default.
- W2891933988 hasConcept C138885662 @default.
- W2891933988 hasConcept C154945302 @default.
- W2891933988 hasConcept C162324750 @default.
- W2891933988 hasConcept C173853756 @default.
- W2891933988 hasConcept C177264268 @default.
- W2891933988 hasConcept C187736073 @default.
- W2891933988 hasConcept C199360897 @default.
- W2891933988 hasConcept C204321447 @default.
- W2891933988 hasConcept C2777200299 @default.
- W2891933988 hasConcept C2780009758 @default.
- W2891933988 hasConcept C2780451532 @default.
- W2891933988 hasConcept C28490314 @default.
- W2891933988 hasConcept C37736160 @default.
- W2891933988 hasConcept C41008148 @default.
- W2891933988 hasConcept C41895202 @default.
- W2891933988 hasConcept C57273362 @default.
- W2891933988 hasConceptScore W2891933988C11413529 @default.
- W2891933988 hasConceptScore W2891933988C119857082 @default.
- W2891933988 hasConceptScore W2891933988C124101348 @default.
- W2891933988 hasConceptScore W2891933988C136764020 @default.
- W2891933988 hasConceptScore W2891933988C138885662 @default.
- W2891933988 hasConceptScore W2891933988C154945302 @default.
- W2891933988 hasConceptScore W2891933988C162324750 @default.
- W2891933988 hasConceptScore W2891933988C173853756 @default.
- W2891933988 hasConceptScore W2891933988C177264268 @default.
- W2891933988 hasConceptScore W2891933988C187736073 @default.
- W2891933988 hasConceptScore W2891933988C199360897 @default.
- W2891933988 hasConceptScore W2891933988C204321447 @default.
- W2891933988 hasConceptScore W2891933988C2777200299 @default.
- W2891933988 hasConceptScore W2891933988C2780009758 @default.
- W2891933988 hasConceptScore W2891933988C2780451532 @default.
- W2891933988 hasConceptScore W2891933988C28490314 @default.
- W2891933988 hasConceptScore W2891933988C37736160 @default.
- W2891933988 hasConceptScore W2891933988C41008148 @default.
- W2891933988 hasConceptScore W2891933988C41895202 @default.
- W2891933988 hasConceptScore W2891933988C57273362 @default.
- W2891933988 hasLocation W28919339881 @default.
- W2891933988 hasOpenAccess W2891933988 @default.
- W2891933988 hasPrimaryLocation W28919339881 @default.
- W2891933988 hasRelatedWork W103938586 @default.
- W2891933988 hasRelatedWork W1968552888 @default.
- W2891933988 hasRelatedWork W2098987383 @default.
- W2891933988 hasRelatedWork W2104718772 @default.
- W2891933988 hasRelatedWork W2117933979 @default.
- W2891933988 hasRelatedWork W2283130723 @default.
- W2891933988 hasRelatedWork W2502115930 @default.
- W2891933988 hasRelatedWork W2795961259 @default.
- W2891933988 hasRelatedWork W3048853838 @default.
- W2891933988 hasRelatedWork W4298396513 @default.
- W2891933988 hasVolume "54" @default.
- W2891933988 isParatext "false" @default.
- W2891933988 isRetracted "false" @default.
- W2891933988 magId "2891933988" @default.
- W2891933988 workType "article" @default.