Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization

North American Chapter of the Association for Computational Linguistics (NAACL)(2022)

引用 21|浏览35
暂无评分
摘要
Neural abstractive summarization models are prone to generate summaries which are factually inconsistent with their source documents. Previous work has introduced the task of recognizing such factual inconsistency as a downstream application of natural language inference (NLI). However, state-of-the-art NLI models perform poorly in this context due to their inability to generalize to the target task. In this work, we show that NLI models can be effective for this task when the training data is augmented with high-quality task-oriented examples. We introduce Falsesum, a data generation pipeline leveraging a controllable text generation model to perturb human-annotated summaries, introducing varying types of factual inconsistencies. Unlike previously introduced document-level NLI datasets, our generated dataset contains examples that are diverse and inconsistent yet plausible. We show that models trained on a Falsesum-augmented NLI dataset improve the state-of-the-art performance across four benchmarks for detecting factual inconsistency in summarization. The code to obtain the dataset is available online at https://github.com/joshbambrick/Falsesum
更多
查看译文
关键词
factual inconsistency,examples,document-level
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要