Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788085213> ?p ?o ?g. }
- W2788085213 abstract "User feedback can be an effective indicator to the success of the human-robot conversation. However, to avoid to interrupt the online real-time conversation process, explicit feedback is usually gained at the end of a conversation. Alternatively, users' responses usually contain their implicit feedback, such as stance, sentiment, emotion, etc., towards the conversation content or the interlocutors. Therefore, exploring the implicit feedback is a natural way to optimize the conversation generation process. In this paper, we propose a novel reward function which explores the implicit feedback to optimize the future reward of a reinforcement learning based neural conversation model. A simulation strategy is applied to explore the state-action space in training and test. Experimental results show that the proposed approach outperforms the Seq2Seq model and the state-of-the-art reinforcement learning model for conversation generation on automatic and human evaluations on the OpenSubtitles and Twitter datasets." @default.
- W2788085213 created "2018-03-06" @default.
- W2788085213 creator A5058271872 @default.
- W2788085213 creator A5063089557 @default.
- W2788085213 creator A5063441337 @default.
- W2788085213 creator A5090720315 @default.
- W2788085213 date "2018-04-25" @default.
- W2788085213 modified "2023-09-27" @default.
- W2788085213 title "Exploring Implicit Feedback for Open Domain Conversation Generation" @default.
- W2788085213 cites W10957333 @default.
- W2788085213 cites W1591706642 @default.
- W2788085213 cites W1654173042 @default.
- W2788085213 cites W1847211030 @default.
- W2788085213 cites W1948566616 @default.
- W2788085213 cites W1980340273 @default.
- W2788085213 cites W2101105183 @default.
- W2788085213 cites W2103102929 @default.
- W2788085213 cites W2108239140 @default.
- W2788085213 cites W2115101920 @default.
- W2788085213 cites W2119717200 @default.
- W2788085213 cites W2122514299 @default.
- W2788085213 cites W2130942839 @default.
- W2788085213 cites W2155027007 @default.
- W2788085213 cites W2157716519 @default.
- W2788085213 cites W2160458012 @default.
- W2788085213 cites W2161181481 @default.
- W2788085213 cites W2170973209 @default.
- W2788085213 cites W2204302769 @default.
- W2788085213 cites W2250895046 @default.
- W2788085213 cites W225503657 @default.
- W2788085213 cites W2296073425 @default.
- W2788085213 cites W2335981466 @default.
- W2788085213 cites W2396229782 @default.
- W2788085213 cites W2417401578 @default.
- W2788085213 cites W2470875822 @default.
- W2788085213 cites W2566559207 @default.
- W2788085213 cites W2567406479 @default.
- W2788085213 cites W2951176429 @default.
- W2788085213 cites W2962883855 @default.
- W2788085213 cites W2963035145 @default.
- W2788085213 cites W2963068985 @default.
- W2788085213 cites W2963167310 @default.
- W2788085213 cites W2963206148 @default.
- W2788085213 cites W2963248296 @default.
- W2788085213 cites W2963360026 @default.
- W2788085213 cites W2963790827 @default.
- W2788085213 cites W2963797754 @default.
- W2788085213 cites W2963963856 @default.
- W2788085213 cites W2963986868 @default.
- W2788085213 cites W2964308564 @default.
- W2788085213 cites W2964352131 @default.
- W2788085213 doi "https://doi.org/10.1609/aaai.v32i1.11253" @default.
- W2788085213 hasPublicationYear "2018" @default.
- W2788085213 type Work @default.
- W2788085213 sameAs 2788085213 @default.
- W2788085213 citedByCount "13" @default.
- W2788085213 countsByYear W27880852132018 @default.
- W2788085213 countsByYear W27880852132019 @default.
- W2788085213 countsByYear W27880852132020 @default.
- W2788085213 countsByYear W27880852132021 @default.
- W2788085213 countsByYear W27880852132022 @default.
- W2788085213 countsByYear W27880852132023 @default.
- W2788085213 crossrefType "journal-article" @default.
- W2788085213 hasAuthorship W2788085213A5058271872 @default.
- W2788085213 hasAuthorship W2788085213A5063089557 @default.
- W2788085213 hasAuthorship W2788085213A5063441337 @default.
- W2788085213 hasAuthorship W2788085213A5090720315 @default.
- W2788085213 hasBestOaLocation W27880852131 @default.
- W2788085213 hasConcept C107457646 @default.
- W2788085213 hasConcept C111919701 @default.
- W2788085213 hasConcept C121332964 @default.
- W2788085213 hasConcept C154945302 @default.
- W2788085213 hasConcept C15744967 @default.
- W2788085213 hasConcept C2777200299 @default.
- W2788085213 hasConcept C2780791683 @default.
- W2788085213 hasConcept C41008148 @default.
- W2788085213 hasConcept C41661131 @default.
- W2788085213 hasConcept C46312422 @default.
- W2788085213 hasConcept C62520636 @default.
- W2788085213 hasConcept C761482 @default.
- W2788085213 hasConcept C76155785 @default.
- W2788085213 hasConcept C97541855 @default.
- W2788085213 hasConcept C98045186 @default.
- W2788085213 hasConceptScore W2788085213C107457646 @default.
- W2788085213 hasConceptScore W2788085213C111919701 @default.
- W2788085213 hasConceptScore W2788085213C121332964 @default.
- W2788085213 hasConceptScore W2788085213C154945302 @default.
- W2788085213 hasConceptScore W2788085213C15744967 @default.
- W2788085213 hasConceptScore W2788085213C2777200299 @default.
- W2788085213 hasConceptScore W2788085213C2780791683 @default.
- W2788085213 hasConceptScore W2788085213C41008148 @default.
- W2788085213 hasConceptScore W2788085213C41661131 @default.
- W2788085213 hasConceptScore W2788085213C46312422 @default.
- W2788085213 hasConceptScore W2788085213C62520636 @default.
- W2788085213 hasConceptScore W2788085213C761482 @default.
- W2788085213 hasConceptScore W2788085213C76155785 @default.
- W2788085213 hasConceptScore W2788085213C97541855 @default.
- W2788085213 hasConceptScore W2788085213C98045186 @default.
- W2788085213 hasIssue "1" @default.
- W2788085213 hasLocation W27880852131 @default.