# A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization

arXiv: https://arxiv.org/abs/2203.02894 · HTML: https://mlsanity.com/paper/2203.02894/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 6 Mar 2022.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Backpropagation through the Void: Optimizing control variates for black-box gradient estimation](https://mlsanity.com/paper/1711.00123/) (2017)
- [A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal](https://mlsanity.com/paper/2005.10070/) (2020)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization](https://mlsanity.com/paper/1808.06218/) (2018)
- [Improving Abstraction in Text Summarization](https://mlsanity.com/paper/1808.07913/) (2018)
- [Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning](https://mlsanity.com/paper/2010.00117/) (2020)
- [Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization](https://mlsanity.com/paper/1909.00141/) (2019)
- [Cold-Start Reinforcement Learning with Softmax Policy Gradient](https://mlsanity.com/paper/1709.09346/) (2017)
- [DynE: Dynamic Ensemble Decoding for Multi-Document Summarization](https://mlsanity.com/paper/2006.08748/) (2020)
- [RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation](https://mlsanity.com/paper/2106.04080/) (2021)

## Built on by (most cited first, 1 of 1)

- [Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers](https://mlsanity.com/paper/2308.13191/) (2023)

## Abstract (arXiv)

Multi-document summarization (MDS) has made significant progress in recent years, in part facilitated by the availability of new, dedicated datasets and capacious language models. However, a standing limitation of these models is that they are trained against limited references and with plain maximum-likelihood objectives. As for many other generative tasks, reinforcement learning (RL) offers the potential to improve the training of MDS models; yet, it requires a carefully-designed reward that can ensure appropriate leverage of both the reference summaries and the input documents. For this reason, in this paper we propose fine-tuning an MDS baseline with a reward that balances a reference-based metric such as ROUGE with coverage of the input documents. To implement the approach, we utilize RELAX (Grathwohl et al., 2018), a contemporary gradient estimator which is both low-variance and unbiased, and we fine-tune the baseline in a few-shot style for both stability and computational efficiency. Experimental results over the Multi-News and WCEP MDS datasets show significant improvements of up to +0.95 pp average ROUGE score and +3.17 pp METEOR score over the baseline, and competitive results with the literature. In addition, they show that the coverage of the input documents is increased, and evenly across all documents.