Papers › Augmenting Memory Networks for Rich and Efficient Retrieval in Grounded Dialogue

Augmenting Memory Networks for Rich and Efficient Retrieval in Grounded Dialogue

16 Nov 2021ACL ARR November 2021 11archive 2025-07-28

Anonymous

Grounded dialogue consists of conditioning a conversation on additional latent inputs ("factoids") beyond the dialogue context, such as Wikipedia articles, IMDB reviews, persona, and images. Due to a scarcity of <context, factoid> labels, it is common practice to jointly learn the knowledge-selection and grounded response generation tasks end-to-end. When conditioning the response on these factoids, previous work has either treated the factoids as a weighed average vector, or separately computed probabilities for each <context, factoid> pair. However, the former creates a bottleneck whilst the latter prevents factoids from being considered jointly. Our new method, PolyMemNet, learns a matrix representation of the context and factoids, allowing for multiple factoids to be jointly considered in response selection, without imposing a bottleneck. We show how this achieves up to a 17% boost in knowledge-selection accuracy and 13% in response-selection accuracy versus memory networks.

PaperPDFCode

Code

atticruckverwandlung/augmentingmemorynetworks officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ArticlesResponse GenerationRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections