paper-with-me

홈 › Papers

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

2021-05-29 · ACL 2021 5 · Linzi Xing, Wen Xiao, Giuseppe Carenini

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.

📄 PDF Abstract BibTeX arXiv:2105.14241

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesNews Summarization

Similar Papers 제목 키워드 기반

Leveraging Lead Bias for Zero-shot Abstractive News Summarization

2019-12-25 · Chenguang Zhu, Ziyi Yang, Robert Gmyr, Michael Zeng 외

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 Summarization

Make Lead Bias in Your Favor: A Simple and Effective Method for News Summarization

2019-09-25 · Chenguang Zhu, ZiYi Yang, Robert Gmyr, Michael Zeng 외

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 Summarization

Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization

2019-08-30 · IJCNLP 2019 11 · Taehee Jung, Dongyeop Kang, Lucas Mentch, Eduard Hovy

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 SummarizationPosition

NeuS: Neutral Multi-News Summarization for Framing Bias Mitigation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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 Summarization

Demoting Racial Bias in Hate Speech Detection

2020-05-25 · WS 2020 7 · Mengzhou Xia, Anjalie Field, Yulia Tsvetkov

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