# Joint Parsing and Generation for Abstractive Summarization

arXiv: https://arxiv.org/abs/1911.10389 · HTML: https://mlsanity.com/paper/1911.10389/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2019.

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

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Focus Attention: Promoting Faithfulness and Diversity in Summarization](https://mlsanity.com/paper/2105.11921/) (2021)
- [Challenges in Domain-Specific Abstractive Summarization and How to Overcome them](https://mlsanity.com/paper/2307.00963/) (2023)
- [Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2310.18794/) (2023)
- [Dependency Structure for News Document Summarization](https://mlsanity.com/paper/2109.11199/) (2021)
- [Document-aware Positional Encoding and Linguistic-guided Encoding for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2209.05929/) (2022)

## Abstract (arXiv)

Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its syntactic dependency parse while performing abstraction. If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged. The proposed method thus holds promise for producing grammatical sentences and encouraging the summary to stay true-to-original. Our contributions of this work are twofold. First, we present a novel neural architecture for abstractive summarization that combines a sequential decoder with a tree-based decoder in a synchronized manner to generate a summary sentence and its syntactic parse. Secondly, we describe a novel human evaluation protocol to assess if, and to what extent, a summary remains true to its original meanings. We evaluate our method on a number of summarization datasets and demonstrate competitive results against strong baselines.