Matches in SemOpenAlex for { <https://semopenalex.org/work/W3144328175> ?p ?o ?g. }
- W3144328175 abstract "Dialogue generation has been successfully learned from scratch by neural networks, but tends to produce the same general response, e.g., what are you talking about?, in many conversations. To reduce this homogeneity, external knowledge such as the speaker's profile and domain knowledge is applied as an additional condition to diversify a model's output. The required knowledge to develop an effective conversation, however, is not always available, which is different from prior work's assumption that a model always has acquired sufficient knowledge before chatting. This problem can be detrimental when applying a dialogue model like this chatting online with unconstrained people and topics, because the model does not have the needed knowledge. To address this problem, we propose InjK, which is a two-stage approach to inject knowledge into a dialogue generation model. First, we train a large-scale language model and query it as textual knowledge. Second, we frame a dialogue generation model to sequentially generate textual knowledge and a corresponding response. Empirically, when a dialogue generation model can only access limited knowledge, our method outperforms prior work by producing more coherent and informative responses." @default.
- W3144328175 created "2021-04-13" @default.
- W3144328175 creator A5003799076 @default.
- W3144328175 creator A5016343106 @default.
- W3144328175 creator A5050195037 @default.
- W3144328175 date "2020-04-30" @default.
- W3144328175 modified "2023-09-24" @default.
- W3144328175 title "Knowledge Injection into Dialogue Generation via Language Models" @default.
- W3144328175 cites W1591706642 @default.
- W3144328175 cites W1608475977 @default.
- W3144328175 cites W1964475109 @default.
- W3144328175 cites W1965555277 @default.
- W3144328175 cites W1975879668 @default.
- W3144328175 cites W2024472792 @default.
- W3144328175 cites W2093976733 @default.
- W3144328175 cites W2099471712 @default.
- W3144328175 cites W2121863487 @default.
- W3144328175 cites W2141708418 @default.
- W3144328175 cites W2145688713 @default.
- W3144328175 cites W2164777277 @default.
- W3144328175 cites W2581637843 @default.
- W3144328175 cites W2586847566 @default.
- W3144328175 cites W2734443755 @default.
- W3144328175 cites W2735642330 @default.
- W3144328175 cites W2756487349 @default.
- W3144328175 cites W2807873315 @default.
- W3144328175 cites W2890969459 @default.
- W3144328175 cites W2908510526 @default.
- W3144328175 cites W2913443447 @default.
- W3144328175 cites W2914204778 @default.
- W3144328175 cites W2949433733 @default.
- W3144328175 cites W2949888546 @default.
- W3144328175 cites W2950457956 @default.
- W3144328175 cites W2962717182 @default.
- W3144328175 cites W2962883855 @default.
- W3144328175 cites W2963045354 @default.
- W3144328175 cites W2963085895 @default.
- W3144328175 cites W2963186354 @default.
- W3144328175 cites W2963206148 @default.
- W3144328175 cites W2963223306 @default.
- W3144328175 cites W2963248296 @default.
- W3144328175 cites W2963248455 @default.
- W3144328175 cites W2963403868 @default.
- W3144328175 cites W2963475460 @default.
- W3144328175 cites W2963559013 @default.
- W3144328175 cites W2963790827 @default.
- W3144328175 cites W2963825865 @default.
- W3144328175 cites W2964352131 @default.
- W3144328175 cites W2970252402 @default.
- W3144328175 cites W2971199636 @default.
- W3144328175 cites W2971236040 @default.
- W3144328175 cites W2971869958 @default.
- W3144328175 cites W2982394217 @default.
- W3144328175 cites W2997892440 @default.
- W3144328175 cites W3098824823 @default.
- W3144328175 cites W3103100151 @default.
- W3144328175 hasPublicationYear "2020" @default.
- W3144328175 type Work @default.
- W3144328175 sameAs 3144328175 @default.
- W3144328175 citedByCount "1" @default.
- W3144328175 countsByYear W31443281752021 @default.
- W3144328175 crossrefType "posted-content" @default.
- W3144328175 hasAuthorship W3144328175A5003799076 @default.
- W3144328175 hasAuthorship W3144328175A5016343106 @default.
- W3144328175 hasAuthorship W3144328175A5050195037 @default.
- W3144328175 hasConcept C111919701 @default.
- W3144328175 hasConcept C126042441 @default.
- W3144328175 hasConcept C137293760 @default.
- W3144328175 hasConcept C138885662 @default.
- W3144328175 hasConcept C154945302 @default.
- W3144328175 hasConcept C204321447 @default.
- W3144328175 hasConcept C207685749 @default.
- W3144328175 hasConcept C2777200299 @default.
- W3144328175 hasConcept C2781235140 @default.
- W3144328175 hasConcept C41008148 @default.
- W3144328175 hasConcept C41895202 @default.
- W3144328175 hasConcept C50644808 @default.
- W3144328175 hasConcept C76155785 @default.
- W3144328175 hasConceptScore W3144328175C111919701 @default.
- W3144328175 hasConceptScore W3144328175C126042441 @default.
- W3144328175 hasConceptScore W3144328175C137293760 @default.
- W3144328175 hasConceptScore W3144328175C138885662 @default.
- W3144328175 hasConceptScore W3144328175C154945302 @default.
- W3144328175 hasConceptScore W3144328175C204321447 @default.
- W3144328175 hasConceptScore W3144328175C207685749 @default.
- W3144328175 hasConceptScore W3144328175C2777200299 @default.
- W3144328175 hasConceptScore W3144328175C2781235140 @default.
- W3144328175 hasConceptScore W3144328175C41008148 @default.
- W3144328175 hasConceptScore W3144328175C41895202 @default.
- W3144328175 hasConceptScore W3144328175C50644808 @default.
- W3144328175 hasConceptScore W3144328175C76155785 @default.
- W3144328175 hasLocation W31443281751 @default.
- W3144328175 hasOpenAccess W3144328175 @default.
- W3144328175 hasPrimaryLocation W31443281751 @default.
- W3144328175 hasRelatedWork W1969789795 @default.
- W3144328175 hasRelatedWork W2253068693 @default.
- W3144328175 hasRelatedWork W2253937316 @default.
- W3144328175 hasRelatedWork W2545313930 @default.
- W3144328175 hasRelatedWork W2754194354 @default.
- W3144328175 hasRelatedWork W2786408982 @default.