Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning
In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers, severely limiting their performance on data with different or even no bias. In this paper, we introduce a novel technique to demote lead bias and make the summarizer focus more on the content semantics. Experiments on two news corpora with different degrees of lead bias show that our method can effectively demote the model's learned lead bias and improve its generality on out-of-distribution data, with little to no performance loss on in-distribution data.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesNews SummarizationSimilar Papers 제목 키워드 기반
Leveraging Lead Bias for Zero-shot Abstractive News Summarization
A typical journalistic convention in news articles is to deliver the most salient information in the beginning, also known as the lead bias. While this phenomenon can be exploited in generating a summary, it has a detrim…
ArticlesDomain AdaptationNews SummarizationMake Lead Bias in Your Favor: A Simple and Effective Method for News Summarization
Lead bias is a common phenomenon in news summarization, where early parts of an article often contain the most salient information. While many algorithms exploit this fact in summary generation, it has a detrimental effe…
News SummarizationEarlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization
Despite the recent developments on neural summarization systems, the underlying logic behind the improvements from the systems and its corpus-dependency remains largely unexplored. Position of sentences in the original t…
ArticlesDiversityNews SummarizationPositionNeuS: Neutral Multi-News Summarization for Framing Bias Mitigation
Media framing bias can lead to increased political polarization, and thus, the need for automatic mitigation methods is growing. We propose a new task, a \textit{neutral} summary generation from multiple news articles of…
ArticlesNews SummarizationDemoting Racial Bias in Hate Speech Detection
In current hate speech datasets, there exists a high correlation between annotators' perceptions of toxicity and signals of African American English (AAE). This bias in annotated training data and the tendency of machine…
Hate Speech Detection