# Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation

arXiv: https://arxiv.org/abs/1908.09528 · HTML: https://mlsanity.com/paper/1908.09528/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 12 of 12)

- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems](https://mlsanity.com/paper/2109.04084/) (2021)
- [Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation](https://mlsanity.com/paper/2102.09282/) (2021)
- [RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models](https://mlsanity.com/paper/2110.07477/) (2021)
- [Wizard of Search Engine: Access to Information Through Conversations with Search Engines](https://mlsanity.com/paper/2105.08301/) (2021)
- [Human-like informative conversations: Better acknowledgements using conditional mutual information](https://mlsanity.com/paper/2104.07831/) (2021)
- [Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks](https://mlsanity.com/paper/2105.10323/) (2021)
- [Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access](https://mlsanity.com/paper/2212.05373/) (2022)
- [Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion](https://mlsanity.com/paper/2204.11239/) (2022)
- [Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoring](https://mlsanity.com/paper/2310.13566/) (2023)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)
- [Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue](https://mlsanity.com/paper/2410.15970/) (2024)

## Abstract (arXiv)

Background Based Conversations (BBCs) have been introduced to help conversational systems avoid generating overly generic responses. In a BBC, the conversation is grounded in a knowledge source. A key challenge in BBCs is Knowledge Selection (KS): given a conversational context, try to find the appropriate background knowledge (a text fragment containing related facts or comments, etc.) based on which to generate the next response. Previous work addresses KS by employing attention and/or pointer mechanisms. These mechanisms use a local perspective, i.e., they select a token at a time based solely on the current decoding state. We argue for the adoption of a global perspective, i.e., pre-selecting some text fragments from the background knowledge that could help determine the topic of the next response. We enhance KS in BBCs by introducing a Global-to-Local Knowledge Selection (GLKS) mechanism. Given a conversational context and background knowledge, we first learn a topic transition vector to encode the most likely text fragments to be used in the next response, which is then used to guide the local KS at each decoding timestamp. In order to effectively learn the topic transition vector, we propose a distantly supervised learning schema. Experimental results show that the GLKS model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluation. More importantly, GLKS achieves this without requiring any extra annotations, which demonstrates its high degree of scalability.