# Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation

arXiv: https://arxiv.org/abs/2102.09282 · HTML: https://mlsanity.com/paper/2102.09282/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 18 Feb 2021.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://mlsanity.com/paper/1506.08909/) (2015)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service](https://mlsanity.com/paper/1911.09969/) (2019)
- [CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation](https://mlsanity.com/paper/2005.00329/) (2020)
- [Hierarchical Recurrent Attention Network for Response Generation](https://mlsanity.com/paper/1701.07149/) (2017)
- [ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation](https://mlsanity.com/paper/1907.05339/) (2019)
- [Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity](https://mlsanity.com/paper/1809.06873/) (2018)
- [Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables](https://mlsanity.com/paper/1906.07429/) (2019)
- [User-Inspired Posterior Network for Recommendation Reason Generation](https://mlsanity.com/paper/2102.07919/) (2021)
- [Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation](https://mlsanity.com/paper/1908.09528/) (2019)
- [Familia: A Configurable Topic Modeling Framework for Industrial Text Engineering](https://mlsanity.com/paper/1808.03733/) (2018)
- [Compose Like Humans: Jointly Improving the Coherence and Novelty for Modern Chinese Poetry Generation](https://mlsanity.com/paper/2005.01556/) (2020)

## Built on by (most cited first, 14 of 14)

- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [Probing Product Description Generation via Posterior Distillation](https://mlsanity.com/paper/2103.01594/) (2021)
- [Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization](https://mlsanity.com/paper/2109.06471/) (2021)
- [Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents](https://mlsanity.com/paper/2602.13234/) (2026)
- [Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory](https://mlsanity.com/paper/2607.00017/) (2026)
- [DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution](https://mlsanity.com/paper/2603.19248/) (2026)
- [SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis](https://mlsanity.com/paper/2108.02572/) (2021)
- [VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search](https://mlsanity.com/paper/2108.02725/) (2021)
- [Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation](https://mlsanity.com/paper/2109.05778/) (2021)
- [Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors](https://mlsanity.com/paper/2202.02830/) (2022)
- [Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks](https://mlsanity.com/paper/2203.11011/) (2022)
- [Explanation-Guided Fairness Testing through Genetic Algorithm](https://mlsanity.com/paper/2205.08335/) (2022)
- [Using Graph Neural Networks for Program Termination](https://mlsanity.com/paper/2207.14648/) (2022)
- [Tribe or Not? Critical Inspection of Group Differences Using TribalGram](https://mlsanity.com/paper/2303.09664/) (2023)

## Abstract (arXiv)

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for multi-turn dialogue generation. However, existing methods cannot differentiate both useful words and utterances in long distances from a response. Besides, previous work just performs context selection based on a state in the decoder, which lacks a global guidance and could lead some focuses on irrelevant or unnecessary information. In this paper, we propose a novel model with hierarchical self-attention mechanism and distant supervision to not only detect relevant words and utterances in short and long distances, but also discern related information globally when decoding. Experimental results on two public datasets of both automatic and human evaluations show that our model significantly outperforms other baselines in terms of fluency, coherence, and informativeness.