mlsanityData to 7 Oct 2026

Subjective Bias in Abstractive Summarization

arXiv 2106.10084 ↗First posted 18 Jun 2021cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 18 Jun 2021.

Builds on

19 of 23 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  7. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  8. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  9. 2015Teaching Machines to Read and Comprehendcited by 1,039
  10. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  11. 2019Text Summarization with Pretrained Encoderscited by 553
  12. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
7 more
  1. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  2. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  3. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
  4. 2018Graph-to-Sequence Learning using Gated Graph Neural Networkscited by 61
  5. 2019An Editorial Network for Enhanced Document Summarizationcited by 5
  6. 2019In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processescited by 4
  7. 2016Distraction-Based Neural Networks for Document Summarizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 0; 2025: 0; 2026: 1.

5 papers.

  1. 2023Evaluation of African American Language Bias in Natural Language Generationcited by 36
  2. 2023It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performancecited by 25
  3. 2022EntSUM: A Data Set for Entity-Centric Summarizationcited by 22
  4. 2026BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Modelscited by 1
  5. 2023Exploiting Representation Bias for Data Distillation in Abstractive Text Summarizationcited by 0