Subjective Bias in Abstractive Summarization

06/18/2021
by   Lei Li, et al.
0

Due to the subjectivity of the summarization, it is a good practice to have more than one gold summary for each training document. However, many modern large-scale abstractive summarization datasets have only one-to-one samples written by different human with different styles. The impact of this phenomenon is understudied. We formulate the differences among possible multiple expressions summarizing the same content as subjective bias and examine the role of this bias in the context of abstractive summarization. In this paper a lightweight and effective method to extract the feature embeddings of subjective styles is proposed. Results of summarization models trained on style-clustered datasets show that there are certain types of styles that lead to better convergence, abstraction and generalization. The reproducible code and generated summaries are available online.

READ FULL TEXT

page 6

page 8

research
04/04/2020

Hooks in the Headline: Learning to Generate Headlines with Controlled Styles

Current summarization systems only produce plain, factual headlines, but...
research
01/03/2020

TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising

Text summarization aims to extract essential information from a piece of...
research
10/18/2018

WikiHow: A Large Scale Text Summarization Dataset

Sequence-to-sequence models have recently gained the state of the art pe...
research
11/28/2016

Improving Multi-Document Summarization via Text Classification

Developed so far, multi-document summarization has reached its bottlenec...
research
04/05/2021

Inference Time Style Control for Summarization

How to generate summaries of different styles without requiring corpora ...
research
10/08/2021

Evaluation of Summarization Systems across Gender, Age, and Race

Summarization systems are ultimately evaluated by human annotators and r...
research
03/28/2023

That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentation

Segmentation uncertainty models predict a distribution over plausible se...

Please sign up or login with your details

Forgot password? Click here to reset