Matches in SemOpenAlex for { <https://semopenalex.org/work/W2888914530> ?p ?o ?g. }
- W2888914530 abstract "We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing $50) and the execution of that strategy (e.g., generating The bike is brand new. Selling for just $50.). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse di- alogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches." @default.
- W2888914530 created "2018-09-07" @default.
- W2888914530 creator A5025255782 @default.
- W2888914530 creator A5030141940 @default.
- W2888914530 creator A5086343573 @default.
- W2888914530 creator A5086654042 @default.
- W2888914530 date "2018-08-29" @default.
- W2888914530 modified "2023-09-24" @default.
- W2888914530 title "Decoupling Strategy and Generation in Negotiation Dialogues" @default.
- W2888914530 cites W1518951372 @default.
- W2888914530 cites W1521219245 @default.
- W2888914530 cites W1830940278 @default.
- W2888914530 cites W1920532145 @default.
- W2888914530 cites W1975244201 @default.
- W2888914530 cites W2001050921 @default.
- W2888914530 cites W2136152952 @default.
- W2888914530 cites W2166100419 @default.
- W2888914530 cites W2174703168 @default.
- W2888914530 cites W2246008130 @default.
- W2888914530 cites W2250539671 @default.
- W2888914530 cites W2405601855 @default.
- W2888914530 cites W2410983263 @default.
- W2888914530 cites W2468710617 @default.
- W2888914530 cites W2579198228 @default.
- W2888914530 cites W2593751037 @default.
- W2888914530 cites W2594726847 @default.
- W2888914530 cites W2605246398 @default.
- W2888914530 cites W2618681852 @default.
- W2888914530 cites W2769917417 @default.
- W2888914530 cites W2786533521 @default.
- W2888914530 cites W2886444114 @default.
- W2888914530 cites W2950037544 @default.
- W2888914530 cites W2951520714 @default.
- W2888914530 cites W2962852262 @default.
- W2888914530 cites W2963068985 @default.
- W2888914530 cites W2963217826 @default.
- W2888914530 cites W2963797754 @default.
- W2888914530 cites W2963993719 @default.
- W2888914530 cites W2964210218 @default.
- W2888914530 doi "https://doi.org/10.48550/arxiv.1808.09637" @default.
- W2888914530 hasPublicationYear "2018" @default.
- W2888914530 type Work @default.
- W2888914530 sameAs 2888914530 @default.
- W2888914530 citedByCount "3" @default.
- W2888914530 countsByYear W28889145302019 @default.
- W2888914530 countsByYear W28889145302021 @default.
- W2888914530 crossrefType "posted-content" @default.
- W2888914530 hasAuthorship W2888914530A5025255782 @default.
- W2888914530 hasAuthorship W2888914530A5030141940 @default.
- W2888914530 hasAuthorship W2888914530A5086343573 @default.
- W2888914530 hasAuthorship W2888914530A5086654042 @default.
- W2888914530 hasBestOaLocation W28889145301 @default.
- W2888914530 hasConcept C101468663 @default.
- W2888914530 hasConcept C111919701 @default.
- W2888914530 hasConcept C119857082 @default.
- W2888914530 hasConcept C127413603 @default.
- W2888914530 hasConcept C133731056 @default.
- W2888914530 hasConcept C151730666 @default.
- W2888914530 hasConcept C154945302 @default.
- W2888914530 hasConcept C17744445 @default.
- W2888914530 hasConcept C199539241 @default.
- W2888914530 hasConcept C199776023 @default.
- W2888914530 hasConcept C202269582 @default.
- W2888914530 hasConcept C205606062 @default.
- W2888914530 hasConcept C2779343474 @default.
- W2888914530 hasConcept C41008148 @default.
- W2888914530 hasConcept C54355233 @default.
- W2888914530 hasConcept C86803240 @default.
- W2888914530 hasConcept C97541855 @default.
- W2888914530 hasConceptScore W2888914530C101468663 @default.
- W2888914530 hasConceptScore W2888914530C111919701 @default.
- W2888914530 hasConceptScore W2888914530C119857082 @default.
- W2888914530 hasConceptScore W2888914530C127413603 @default.
- W2888914530 hasConceptScore W2888914530C133731056 @default.
- W2888914530 hasConceptScore W2888914530C151730666 @default.
- W2888914530 hasConceptScore W2888914530C154945302 @default.
- W2888914530 hasConceptScore W2888914530C17744445 @default.
- W2888914530 hasConceptScore W2888914530C199539241 @default.
- W2888914530 hasConceptScore W2888914530C199776023 @default.
- W2888914530 hasConceptScore W2888914530C202269582 @default.
- W2888914530 hasConceptScore W2888914530C205606062 @default.
- W2888914530 hasConceptScore W2888914530C2779343474 @default.
- W2888914530 hasConceptScore W2888914530C41008148 @default.
- W2888914530 hasConceptScore W2888914530C54355233 @default.
- W2888914530 hasConceptScore W2888914530C86803240 @default.
- W2888914530 hasConceptScore W2888914530C97541855 @default.
- W2888914530 hasLocation W28889145301 @default.
- W2888914530 hasOpenAccess W2888914530 @default.
- W2888914530 hasPrimaryLocation W28889145301 @default.
- W2888914530 hasRelatedWork W1979331590 @default.
- W2888914530 hasRelatedWork W2261683202 @default.
- W2888914530 hasRelatedWork W2292969843 @default.
- W2888914530 hasRelatedWork W2312530137 @default.
- W2888914530 hasRelatedWork W2533925791 @default.
- W2888914530 hasRelatedWork W2914100487 @default.
- W2888914530 hasRelatedWork W2947287992 @default.
- W2888914530 hasRelatedWork W2969966185 @default.
- W2888914530 hasRelatedWork W2978829571 @default.
- W2888914530 hasRelatedWork W2979363950 @default.
- W2888914530 hasRelatedWork W2980784261 @default.