Subjective Bias in Abstractive Summarization
- URL: http://arxiv.org/abs/2106.10084v1
- Date: Fri, 18 Jun 2021 12:17:55 GMT
- Title: Subjective Bias in Abstractive Summarization
- Authors: Lei Li, Wei Liu, Marina Litvak, Natalia Vanetik, Jiacheng Pei, Yinan
Liu, Siya Qi
- Abstract summary: 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.
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.
- Score: 11.675414451656568
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Bias in Opinion Summarisation from Pre-training to Adaptation: A Case
Study in Political Bias [4.964212137957899]
Opinion summarisation aims to summarise the salient information and opinions presented in documents such as product reviews, discussion forums, and social media texts.
generating biased summaries has the risk of potentially swaying public opinion.
arXiv Detail & Related papers (2024-02-01T04:15:59Z) - OpineSum: Entailment-based self-training for abstractive opinion
summarization [6.584115526134759]
We present a novel self-training approach, OpineSum, for abstractive opinion summarization.
The summaries in this approach are built using a novel application of textual entailment.
OpineSum achieves state-of-the-art performance in both settings.
arXiv Detail & Related papers (2022-12-21T06:20:28Z) - Correcting Diverse Factual Errors in Abstractive Summarization via
Post-Editing and Language Model Infilling [56.70682379371534]
We show that our approach vastly outperforms prior methods in correcting erroneous summaries.
Our model -- FactEdit -- improves factuality scores by over 11 points on CNN/DM and over 31 points on XSum.
arXiv Detail & Related papers (2022-10-22T07:16:19Z) - Salience Allocation as Guidance for Abstractive Summarization [61.31826412150143]
We propose a novel summarization approach with a flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as Guidance for Abstractive SummarizatiON)
SEASON utilizes the allocation of salience expectation to guide abstractive summarization and adapts well to articles in different abstractiveness.
arXiv Detail & Related papers (2022-10-22T02:13:44Z) - To Point or Not to Point: Understanding How Abstractive Summarizers
Paraphrase Text [4.4044968357361745]
We characterize how one popular abstractive model, the pointer-generator model of See et al., uses its explicit copy/generation switch to control its level of abstraction.
When we modify the copy/generation switch and force the model to generate, only simple neural abilities are revealed alongside factual inaccuracies and hallucinations.
In line with previous research, these results suggest that abstractive summarization models lack the semantic understanding necessary to generate paraphrases that are both abstractive and faithful to the source document.
arXiv Detail & Related papers (2021-06-03T04:03:15Z) - GSum: A General Framework for Guided Neural Abstractive Summarization [102.29593069542976]
We propose a general and guided summarization framework (GSum) that can effectively take different kinds of external guidance as input.
Experiments demonstrate that this model is effective, achieving state-of-the-art performance according to ROUGE on 4 popular summarization datasets.
arXiv Detail & Related papers (2020-10-15T20:46:14Z) - Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection.
Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text.
Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
arXiv Detail & Related papers (2020-10-06T02:51:02Z) - Few-Shot Learning for Opinion Summarization [117.70510762845338]
Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents.
In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text.
Our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.
arXiv Detail & Related papers (2020-04-30T15:37:38Z) - Unsupervised Opinion Summarization with Noising and Denoising [85.49169453434554]
We create a synthetic dataset from a corpus of user reviews by sampling a review, pretending it is a summary, and generating noisy versions thereof.
At test time, the model accepts genuine reviews and generates a summary containing salient opinions, treating those that do not reach consensus as noise.
arXiv Detail & Related papers (2020-04-21T16:54:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.