# Reinforcing Semantic-Symmetry for Document Summarization

arXiv: https://arxiv.org/abs/2112.07583 · HTML: https://mlsanity.com/paper/2112.07583/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization](https://mlsanity.com/paper/1906.03741/) (2019)
- [Dual Learning for Machine Translation](https://mlsanity.com/paper/1611.00179/) (2016)
- [Ranking Sentences for Extractive Summarization with Reinforcement Learning](https://mlsanity.com/paper/1802.08636/) (2018)
- [Multi-Reward Reinforced Summarization with Saliency and Entailment](https://mlsanity.com/paper/1804.06451/) (2018)
- [A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss](https://mlsanity.com/paper/1805.06266/) (2018)
- [Topic-Aware Neural Keyphrase Generation for Social Media Language](https://mlsanity.com/paper/1906.03889/) (2019)
- [An Entity-Driven Framework for Abstractive Summarization](https://mlsanity.com/paper/1909.02059/) (2019)
- [Deep Recurrent Generative Decoder for Abstractive Text Summarization](https://mlsanity.com/paper/1708.00625/) (2017)
- [DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization](https://mlsanity.com/paper/1811.02394/) (2018)
- [An Editorial Network for Enhanced Document Summarization](https://mlsanity.com/paper/1902.10360/) (2019)
- [Attention Optimization for Abstractive Document Summarization](https://mlsanity.com/paper/1910.11491/) (2019)

## Abstract (arXiv)

Document summarization condenses a long document into a short version with salient information and accurate semantic descriptions. The main issue is how to make the output summary semantically consistent with the input document. To reach this goal, recently, researchers have focused on supervised end-to-end hybrid approaches, which contain an extractor module and abstractor module. Among them, the extractor identifies the salient sentences from the input document, and the abstractor generates a summary from the salient sentences. This model successfully keeps the consistency between the generated summary and the reference summary via various strategies (e.g., reinforcement learning). There are two semantic gaps when training the hybrid model (one is between document and extracted sentences, and the other is between extracted sentences and summary). However, they are not explicitly considered in the existing methods, which usually results in a semantic bias of summary. To mitigate the above issue, in this paper, a new reinforcing semantic-symmetry learning model is proposed for document summarization (ReSyM). ReSyM introduces a semantic-consistency reward in the extractor to bridge the first gap. A semantic dual-reward is designed to bridge the second gap in the abstractor. The whole document summarization process is implemented via reinforcement learning with a hybrid reward mechanism (combining the above two rewards). Moreover, a comprehensive sentence representation learning method is presented to sufficiently capture the information from the original document. A series of experiments have been conducted on two wildly used benchmark datasets CNN/Daily Mail and BigPatent. The results have shown the superiority of ReSyM by comparing it with the state-of-the-art baselines in terms of various evaluation metrics.