# Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue

arXiv: https://arxiv.org/abs/2002.07510 · HTML: https://mlsanity.com/paper/2002.07510/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2020.

## Built on by (most cited first, 30 of 82)

- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [A Survey of Knowledge Enhanced Pre-trained Language Models](https://mlsanity.com/paper/2211.05994/) (2022)
- [Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features](https://mlsanity.com/paper/2107.06963/) (2021)
- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)
- [Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog](https://mlsanity.com/paper/2102.04643/) (2021)
- [Multimodal Dialogue Response Generation](https://mlsanity.com/paper/2110.08515/) (2021)
- [Semi-Supervised Variational Reasoning for Medical Dialogue Generation](https://mlsanity.com/paper/2105.06071/) (2021)
- [Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters](https://mlsanity.com/paper/2105.06232/) (2021)
- [Multi-Stage Prompting for Knowledgeable Dialogue Generation](https://mlsanity.com/paper/2203.08745/) (2022)
- [DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization](https://mlsanity.com/paper/2109.04673/) (2021)
- [Maria: A Visual Experience Powered Conversational Agent](https://mlsanity.com/paper/2105.13073/) (2021)
- [A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2109.04096/) (2021)
- [DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation](https://mlsanity.com/paper/2204.09149/) (2022)
- [KILM: Knowledge Injection into Encoder-Decoder Language Models](https://mlsanity.com/paper/2302.09170/) (2023)
- [Data-to-text Generation with Variational Sequential Planning](https://mlsanity.com/paper/2202.13756/) (2022)
- [Learning to Select External Knowledge with Multi-Scale Negative Sampling](https://mlsanity.com/paper/2102.02096/) (2021)
- [There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory](https://mlsanity.com/paper/2204.02624/) (2022)
- [Generative Knowledge Selection for Knowledge-Grounded Dialogues](https://mlsanity.com/paper/2304.04836/) (2023)
- [Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems](https://mlsanity.com/paper/2109.04314/) (2021)
- [Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation](https://mlsanity.com/paper/2109.05487/) (2021)
- [BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets](https://mlsanity.com/paper/2210.12687/) (2022)
- [Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs](https://mlsanity.com/paper/2206.07296/) (2022)
- [Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation](https://mlsanity.com/paper/2211.01587/) (2022)
- [TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge](https://mlsanity.com/paper/2203.08517/) (2022)
- [Medical Dialogue Response Generation with Pivotal Information Recalling](https://mlsanity.com/paper/2206.08611/) (2022)
- [Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge](https://mlsanity.com/paper/2206.14000/) (2022)
- [Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs](https://mlsanity.com/paper/2302.11849/) (2023)
- [Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference](https://mlsanity.com/paper/2306.01153/) (2023)

## Abstract (arXiv)

Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge; as a result, it can not only reduce the ambiguity caused from the diversity in knowledge selection of conversation but also better leverage the response information for proper choice of knowledge. Our experimental results show that the proposed model improves the knowledge selection accuracy and subsequently the performance of utterance generation. We achieve the new state-of-the-art performance on Wizard of Wikipedia (Dinan et al., 2019) as one of the most large-scale and challenging benchmarks. We further validate the effectiveness of our model over existing conversation methods in another knowledge-based dialogue Holl-E dataset (Moghe et al., 2018).