paper-with-me

홈 › Papers

Augmenting Memory Networks for Rich and Efficient Retrieval in Grounded Dialogue

2021-11-16 · ACL ARR November 2021 11 · 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.

📄 PDF Abstract BibTeX

Code (1)

atticruckverwandlung/augmentingmemorynetworks 공식 구현 pytorch

Tasks

ArticlesResponse GenerationRetrieval

Similar Papers 제목 키워드 기반

Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters

2021-05-13 · dialdoc (ACL) 2022 5 · Yan Xu, Etsuko Ishii, Samuel Cahyawijaya, Zihan Liu 외

To diversify and enrich generated dialogue responses, knowledge-grounded dialogue has been investigated in recent years. The existing methods tackle the knowledge grounding challenge by retrieving the relevant sentences …

Response GenerationRetrieval

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

2026-08-02 · Jingyu Sun, Yuyang Xue, Mingyang Li, Zhengtao Yao 외 arxiv

Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable,…

Answer Generation

Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation

2023-05-02 · Haolan Zhan, Sameen Maruf, Lizhen Qu, YuFei Wang 외

Flowchart-grounded troubleshooting dialogue (FTD) systems, which follow the instructions of a flowchart to diagnose users' problems in specific domains (e.g., vehicle, laptop), have been gaining research interest in rece…

Data AugmentationResponse GenerationRetrievalSynthetic Data Generation

Hexa: Self-Improving for Knowledge-Grounded Dialogue System

2023-10-10 · DaeJin Jo, Daniel Wontae Nam, Gunsoo Han, Kyoung-Woon On 외

A common practice in knowledge-grounded dialogue generation is to explicitly utilize intermediate steps (e.g., web-search, memory retrieval) with modular approaches. However, data for such steps are often inaccessible co…

Dialogue GenerationDiversityRetrieval

An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

2022-10-30 · Yuxiang Wu, Yu Zhao, Baotian Hu, Pasquale Minervini 외

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model that stores knowledge in its parameters, or…

Computational EfficiencyQuestion AnsweringRetrieval