Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization

By Haoran Li, Junnan Zhu, Jiajun Zhang, Chengqing Zong. 2018

104 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey (2022, background): “, 2021), and (3) using text entailment to develop loss functions to improve fidelity (Falke et al., 2019; Li et al., 2018).”
Survey of Hallucination in Natural Language Generation (2022, methodology): “[103] combine an entailment task with abstractive summarization to encourage models to generate summaries entailed by and faithful to the source.”
Evaluating the Factual Consistency of Abstractive Text Summarization (2019, methodology): “…model outputs used for annotation were provided by the authors of papers: Hsu et al. (2018); Gehrmann et al. (2018); Jiang and Bansal (2018); Chen and Bansal (2018); See et al. (2017); Kryściński et al. (2018); Li et al. (2018b); Pasunuru and Bansal (2018); Zhang et al. (2018); Guo et al. (2018).”
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference (2019, methodology): “multi-task learning with NLI (Li et al., 2018; Pasunuru et al., 2017) to successfully improve the correctness of abstractive sentence summaries.”
Factual Error Correction for Abstractive Summarization Models (2020, background): “Previous work on factual consistency in abstractive summarization can be divided into two categories: abstractive summarization models tailored towards factual consistency (Cao et al., 2018; Zhang et al., 2019b; Li et al., 2018), and evaluation models for factual consistency in abstractive summariza”
Evaluating Factuality in Generation with Dependency-level Entailment (2020, background): “Other work additionally incorporates a reward for generating summaries entailed by the the input (Li et al., 2018; Pasunuru and Bansal, 2018).”
Concept Pointer Network for Abstractive Summarization (2019, methodology): “-MTL-ERAM† (Li et al., 2018) 35.”
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization (2021, background): “(2) Use natural language inference or question answering models for fact checking correction (Li et al., 2018; Falke et al., 2019; Wang et al., 2020; Dong et al., 2020; Durmus et al., 2020; Chen et al., 2020).”
HighRES: Highlight-based Reference-less Evaluation of Summarization (2019, methodology): “Finally, a small number of work evaluates the ”Correctness” (Chen and Bansal, 2018; Li et al., 2018b; Chen and Bansal, 2018) of the summary, similar to fact checking (Vlachos and Riedel, 2014), which can be a challenging task in its own right.”
Multi-Fact Correction in Abstractive Text Summarization (2020, background): “However, in reality this often fails as the models have a high propensity for leaning towards informativeness than correctness (Li et al., 2018).”
Enhancing Factual Consistency of Abstractive Summarization (2021, background): “Li et al. (2018) co-trains summarization and entailment and employs an entailment-aware decoder.”