FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204697369> ?p ?o ?g. }

• W3204697369 abstract "The task of Conversational Recommendation System (CRS), i.e., recommender dialog system, aims to recommend precise items to users through natural language interactions. Though recent end-to-end neural models have shown promising progress on this task, two key challenges still remain. First, the recommended items cannot be always incorporated into the generated response precisely and appropriately. Second, only the items mentioned in the training corpus have a chance to be recommended in the conversation. To tackle these challenges, we introduce a novel framework called NTRD for recommender dialogue system that can decouple the dialogue generation from the item recommendation. NTRD has two key components, i.e., response template generator and item selector. The former adopts an encoder-decoder model to generate a response template with slot locations tied to target items, while the latter fills in slot locations with the proper items using a sufficient attention mechanism. Our approach combines the strengths of both classical slot filling approaches (that are generally controllable) and modern neural NLG approaches (that are generally more natural and accurate). Extensive experiments on the benchmark ReDial show our approach significantly outperforms the previous state-of-the-art methods. Besides, our approach has the unique advantage to produce novel items that do not appear in the training set of dialogue corpus. The code is available at https://github.com/jokieleung/NTRD." @default.
• W3204697369 created "2021-10-11" @default.
• W3204697369 creator A5006460081 @default.
• W3204697369 creator A5013997063 @default.
• W3204697369 creator A5031164256 @default.
• W3204697369 creator A5034579880 @default.
• W3204697369 creator A5060116992 @default.
• W3204697369 creator A5066483084 @default.
• W3204697369 creator A5068898095 @default.
• W3204697369 creator A5084564357 @default.
• W3204697369 creator A5084942382 @default.
• W3204697369 date "2021-01-01" @default.
• W3204697369 modified "2023-10-14" @default.
• W3204697369 title "Learning Neural Templates for Recommender Dialogue System" @default.
• W3204697369 cites W1975244201 @default.
• W3204697369 cites W2009415795 @default.
• W3204697369 cites W2054141820 @default.
• W3204697369 cites W2130942839 @default.
• W3204697369 cites W2133012565 @default.
• W3204697369 cites W2153225416 @default.
• W3204697369 cites W2157881433 @default.
• W3204697369 cites W2158515176 @default.
• W3204697369 cites W2295739661 @default.
• W3204697369 cites W2605350416 @default.
• W3204697369 cites W2783215745 @default.
• W3204697369 cites W2798914047 @default.
• W3204697369 cites W2808871448 @default.
• W3204697369 cites W2888515090 @default.
• W3204697369 cites W2891389695 @default.
• W3204697369 cites W2898076813 @default.
• W3204697369 cites W2955416746 @default.
• W3204697369 cites W2962883855 @default.
• W3204697369 cites W2962944953 @default.
• W3204697369 cites W2963201498 @default.
• W3204697369 cites W2963206148 @default.
• W3204697369 cites W2963403868 @default.
• W3204697369 cites W2963790827 @default.
• W3204697369 cites W2963825865 @default.
• W3204697369 cites W2964077278 @default.
• W3204697369 cites W2964112275 @default.
• W3204697369 cites W2964165364 @default.
• W3204697369 cites W2964207259 @default.
• W3204697369 cites W2964210218 @default.
• W3204697369 cites W2970236742 @default.
• W3204697369 cites W2997662139 @default.
• W3204697369 cites W3000779003 @default.
• W3204697369 cites W3035098003 @default.
• W3204697369 cites W3035301094 @default.
• W3204697369 cites W3035355914 @default.
• W3204697369 cites W3080122044 @default.
• W3204697369 cites W3094070895 @default.
• W3204697369 cites W3100790518 @default.
• W3204697369 cites W3101718968 @default.
• W3204697369 cites W3106454043 @default.
• W3204697369 cites W3115944734 @default.
• W3204697369 cites W3116062118 @default.
• W3204697369 cites W3116455257 @default.
• W3204697369 cites W3152509363 @default.
• W3204697369 cites W3155584966 @default.
• W3204697369 cites W3162337509 @default.
• W3204697369 cites W3163631185 @default.
• W3204697369 cites W3170262904 @default.
• W3204697369 cites W3195061894 @default.
• W3204697369 doi "https://doi.org/10.18653/v1/2021.emnlp-main.617" @default.
• W3204697369 hasPublicationYear "2021" @default.
• W3204697369 type Work @default.
• W3204697369 sameAs 3204697369 @default.
• W3204697369 citedByCount "8" @default.
• W3204697369 countsByYear W32046973692021 @default.
• W3204697369 countsByYear W32046973692022 @default.
• W3204697369 countsByYear W32046973692023 @default.
• W3204697369 crossrefType "proceedings-article" @default.
• W3204697369 hasAuthorship W3204697369A5006460081 @default.
• W3204697369 hasAuthorship W3204697369A5013997063 @default.
• W3204697369 hasAuthorship W3204697369A5031164256 @default.
• W3204697369 hasAuthorship W3204697369A5034579880 @default.
• W3204697369 hasAuthorship W3204697369A5060116992 @default.
• W3204697369 hasAuthorship W3204697369A5066483084 @default.
• W3204697369 hasAuthorship W3204697369A5068898095 @default.
• W3204697369 hasAuthorship W3204697369A5084564357 @default.
• W3204697369 hasAuthorship W3204697369A5084942382 @default.
• W3204697369 hasBestOaLocation W32046973691 @default.
• W3204697369 hasConcept C105795698 @default.
• W3204697369 hasConcept C111919701 @default.
• W3204697369 hasConcept C118505674 @default.
• W3204697369 hasConcept C119857082 @default.
• W3204697369 hasConcept C121332964 @default.
• W3204697369 hasConcept C13280743 @default.
• W3204697369 hasConcept C136764020 @default.
• W3204697369 hasConcept C138885662 @default.
• W3204697369 hasConcept C154945302 @default.
• W3204697369 hasConcept C162324750 @default.
• W3204697369 hasConcept C163258240 @default.
• W3204697369 hasConcept C165064840 @default.
• W3204697369 hasConcept C173853756 @default.
• W3204697369 hasConcept C177264268 @default.
• W3204697369 hasConcept C185798385 @default.
• W3204697369 hasConcept C187736073 @default.
• W3204697369 hasConcept C195324797 @default.
• W3204697369 hasConcept C199360897 @default.

• next