Joint Parsing and Generation for Abstractive Summarization

By Kaiqiang Song, Logan Lebanoff, Qipeng Guo, Xipeng Qiu, Xiangyang Xue, Chen Li, Dong Yu, Fei Liu. 2019

30 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Zhe Gan
3. Greg Durrett
4. Jingjing Liu
5. Yu Cheng
6. Tanya Goyal
7. Caiming Xiong
8. Jianfeng Gao

Citations in the corpus

• Multi-Fact Correction in Abstractive Text Summarization (2020, methodology): “On Gigaword, we use the pointer-generator (See et al., 2017), base and full Gen-Parse models (Song et al., 2020) for comparison.”
• Annotating and Modeling Fine-grained Factuality in Summarization (2021, methodology): “, 2020), or constrained decoding (Song et al., 2020a; Mao et al., 2020).”
• Focus Attention: Promoting Faithfulness and Diversity in Summarization (2021, background): “Song et al. (2020) propose to jointly generate a sentence and its syntactic dependency parse to induce grammaticality and faithfulness.”