# Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

arXiv: https://arxiv.org/abs/2206.07296 · HTML: https://mlsanity.com/paper/2206.07296/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation](https://mlsanity.com/paper/2004.04100/) (2020)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [Toward Abstractive Summarization Using Semantic Representations](https://mlsanity.com/paper/1805.10399/) (2018)
- [Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs](https://mlsanity.com/paper/1910.08435/) (2019)
- [Transition-based Parsing with Stack-Transformers](https://mlsanity.com/paper/2010.10669/) (2020)
- [Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading](https://mlsanity.com/paper/1906.02738/) (2019)
- [Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation](https://mlsanity.com/paper/1808.09160/) (2018)
- [RefNet: A Reference-aware Network for Background Based Conversation](https://mlsanity.com/paper/1908.06449/) (2019)
- [DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization](https://mlsanity.com/paper/2109.04673/) (2021)
- [Augmenting End-to-End Dialog Systems with Commonsense Knowledge](https://mlsanity.com/paper/1709.05453/) (2017)
- [Extending Neural Generative Conversational Model using External Knowledge Sources](https://mlsanity.com/paper/1809.05524/) (2018)
- [Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation](https://mlsanity.com/paper/2009.09378/) (2020)
- [An analysis of document graph construction methods for AMR summarization](https://mlsanity.com/paper/2111.13993/) (2021)

## Built on by (most cited first, 11 of 11)

- [Generative Knowledge Selection for Knowledge-Grounded Dialogues](https://mlsanity.com/paper/2304.04836/) (2023)
- [Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation](https://mlsanity.com/paper/2309.08380/) (2023)
- [GraphWOZ: Dialogue Management with Conversational Knowledge Graphs](https://mlsanity.com/paper/2211.12852/) (2022)
- [C-PMI: Conditional Pointwise Mutual Information for Turn-level Dialogue Evaluation](https://mlsanity.com/paper/2306.15245/) (2023)
- [CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations](https://mlsanity.com/paper/2210.02223/) (2022)
- [Defining a New NLP Playground](https://mlsanity.com/paper/2310.20633/) (2023)
- [How Does Knowledge Selection Help Retrieval Augmented Generation?](https://mlsanity.com/paper/2410.13258/) (2024)
- [Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2310.07659/) (2023)
- [Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations](https://mlsanity.com/paper/2310.14340/) (2023)
- [A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation](https://mlsanity.com/paper/2403.03496/) (2024)
- [CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations](https://mlsanity.com/paper/2403.01848/) (2024)

## Abstract (arXiv)

Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection among sentences in the background document. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We jointly apply multi-task learning for sentence-level and concept-level knowledge selection and show that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.