# Multi-hop Inference for Question-driven Summarization

arXiv: https://arxiv.org/abs/2010.03738 · HTML: https://mlsanity.com/paper/2010.03738/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling](https://mlsanity.com/paper/2112.13556/) (2021)
- [A Lightweight Constrained Generation Alternative for Query-focused Summarization](https://mlsanity.com/paper/2304.11721/) (2023)
- [Concise Answers to Complex Questions: Summarization of Long-form Answers](https://mlsanity.com/paper/2305.19271/) (2023)
- [A Topic-aware Summarization Framework with Different Modal Side Information](https://mlsanity.com/paper/2305.11503/) (2023)
- [Few-shot Query-Focused Summarization with Prefix-Merging](https://mlsanity.com/paper/2211.16164/) (2022)
- [AS-ES Learning: Towards Efficient CoT Learning in Small Models](https://mlsanity.com/paper/2403.01969/) (2024)

## Abstract (arXiv)

Question-driven summarization has been recently studied as an effective approach to summarizing the source document to produce concise but informative answers for non-factoid questions. In this work, we propose a novel question-driven abstractive summarization method, Multi-hop Selective Generator (MSG), to incorporate multi-hop reasoning into question-driven summarization and, meanwhile, provide justifications for the generated summaries. Specifically, we jointly model the relevance to the question and the interrelation among different sentences via a human-like multi-hop inference module, which captures important sentences for justifying the summarized answer. A gated selective pointer generator network with a multi-view coverage mechanism is designed to integrate diverse information from different perspectives. Experimental results show that the proposed method consistently outperforms state-of-the-art methods on two non-factoid QA datasets, namely WikiHow and PubMedQA.