Abstractive Summarizers Become Emotional on News Summarization
Source abstract
Abstract
Emotions are central to understanding contemporary journalism; however, they are overlooked in automatic news summarization. Actually, summaries are an entry point to the source article that could favor some emotions to captivate the reader. Nevertheless, the emotional content of summarization corpora and the emotional behavior of summarization models are still unexplored. In this work, we explore the usage of established methodologies to study the emotional content of summarization corpora and the emotional behavior of summarization models. Using these methodologies, we study the emotional content of two widely used summarization corpora: Cnn/Dailymail and Xsum, and the capabilities of three state-of-the-art transformer-based abstractive systems for eliciting emotions in the generated summaries: Bart, Pegasus, and T5. The main significant findings are as follows: (i) emotions are persistent in the two summarization corpora, (ii) summarizers approach moderately well the emotions of the reference summaries, and (iii) more than 75% of the emotions introduced by novel words in generated summaries are present in the reference ones. The combined use of these methodologies has allowed us to conduct a satisfactory study of the emotional content in news summarization.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Advanced Text Analysis Techniques · Natural Language Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 Valencia, Spain
Symanto Symanto Research, C/Reina 12, 46011 Valencia, Spain
Valencian Graduate School and Research Network of Artificial Intelligence (ValgrAI), Universitat Politècnica de Valéncia, 46022 Valencia, Spain
Funding
MCIN/AEI/10.13039/501100011033 · Generalitat Valenciana · Spanish Ministerio de Universidades
References (36)
Show source-provided references
1. Kennedy, A., Kazantseva, A., Inkpen, D., and Szpakowicz, S. (2012, January 28–30). Getting Emotional about News Summarization. Proceedings of the Advances in Artificial Intelligence, Toronto, ON, Canada.10.1007/978-3-642-30353-1_11 ↗
2. On the Role of Emotion in the Future of Journalism
3. The Emotional Turn in Journalism Needs to be About Audience Perceptions
4. Journalism and Emotion
5. Chen, Y., Liu, Y., Chen, L., and Zhang, Y. (2021, January 1–6). DialogSum: A Real-Life Scenario Dialogue Summarization Dataset. Proceedings of the Association for Computational Linguistics: ACL-IJCNLP 2021, Online.10.18653/v1/2021.findings-acl.449 ↗
6. Panchendrarajan, R., Hsu, W., and Li Lee, M. (2021, January 19–23). Emotion-Aware Event Summarization in Microblogs. Proceedings of the Companion Proceedings of the Web Conference 2021, Ljubljana, Slovenia.10.1145/3442442.3452311 ↗
7. Lin, C.Y. (2004). Text Summarization Branches Out, Association for Computational Linguistics.
8. Jumel, C., Louis, A., and Cheung, J.C.K. (2020, January 8). TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.10.18653/v1/2020.emnlp-main.646 ↗
9. Maynez, J., Narayan, S., Bohnet, B., and McDonald, R. (2020, January 5–10). On Faithfulness and Factuality in Abstractive Summarization. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.173 ↗
10. Hermann, K.M., Kočiský, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., and Blunsom, P. (2015, January 7–12). Teaching Machines to Read and Comprehend. Proceedings of the NIPS’15: 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
11. Narayan, S., Cohen, S.B., and Lapata, M. (November, January 31). Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1206 ↗
12. SummEval: Re-evaluating Summarization Evaluation10.1162/tacl_a_00373 ↗
13. Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., and Zettlemoyer, L. (2020, January 5–10). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.703 ↗
14. Zhang, J., Zhao, Y., Saleh, M., and Liu, P.J. (2020, January 13–18). PEGASUS: Pre-Training with Extracted Gap-Sentences for Abstractive Summarization. Proceedings of the 37th International Conference on Machine Learning, Online.
15. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
16. Liu, Y., and Lapata, M. (2019, January 3–7). Text Summarization with Pretrained Encoders. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.10.18653/v1/D19-1387 ↗
17. Zhong, M., Liu, P., Chen, Y., Wang, D., Qiu, X., and Huang, X. (2020, January 5–10). Extractive Summarization as Text Matching. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.10.18653/v1/2020.acl-main.552 ↗
18. Candidate sentence selection for extractive text summarization10.1016/j.ipm.2020.102359 ↗
19. See, A., Liu, P.J., and Manning, C.D. (August, January 30). Get To The Point: Summarization with Pointer-Generator Networks. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, BC, Canada.
20. Gehrmann, S., Deng, Y., and Rush, A. (November, January 31). Bottom-Up Abstractive Summarization. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.10.18653/v1/D18-1443 ↗
21. Planning with Learned Entity Prompts for Abstractive Summarization10.1162/tacl_a_00438 ↗
22. FAR-ASS: Fact-aware reinforced abstractive sentence summarization10.1016/j.ipm.2020.102478 ↗
23. Zhao, Z., Cohen, S.B., and Webber, B. (2020, January 16–20). Reducing Quantity Hallucinations in Abstractive Summarization. Proceedings of the Association for Computational Linguistics: EMNLP 2020, Online.10.18653/v1/2020.findings-emnlp.203 ↗
24. Text summarization using topic-based vector space model and semantic measure10.1016/j.ipm.2021.102536 ↗
25. Dou, Z.Y., Liu, P., Hayashi, H., Jiang, Z., and Neubig, G. (2021, January 6–11). GSum: A General Framework for Guided Neural Abstractive Summarization. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online.10.18653/v1/2021.naacl-main.384 ↗
26. Key phrase aware transformer for abstractive summarization10.1016/j.ipm.2022.102913 ↗
27. Nah, F.F.H., and Siau, K. (2019, January 26–31). The Role of User Emotions for Content Personalization in e-Commerce: Literature Review. Proceedings of the HCI in Business, Government and Organizations. eCommerce and Consumer Behavior, Orlando, FL, USA.
28. Mohammad, S., Bravo-Marquez, F., Salameh, M., and Kiritchenko, S. (2018, January 5–6). SemEval-2018 Task 1: Affect in Tweets. Proceedings of the 12th International Workshop on Semantic Evaluation, New Orleans, LA, USA.10.18653/v1/S18-1001 ↗
29. Overview of the EmoEvalEs task on emotion detection for Spanish at IberLEF 2021
30. A text classification approach to detect psychological stress combining a lexicon-based feature framework with distributional representations10.1016/j.ipm.2022.103011 ↗
31. Negative emotions detection on online mental-health related patients texts using the deep learning with MHA-BCNN model10.1016/j.eswa.2021.115265 ↗
32. What the fake? Probing misinformation detection standing on the shoulder of novelty and emotion10.1016/j.ipm.2021.102740 ↗
33. Mascarell, L., Ruzsics, T., Schneebeli, C., Schlattner, P., Campanella, L., Klingler, S., and Kadar, C. (2021, January 10). Stance Detection in German News Articles. Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), Punta Cana, Dominican Republic.10.18653/v1/2021.fever-1.8 ↗
34. Crowdsourcing a Word-Emotion Association Lexicon10.1111/j.1467-8640.2012.00460.x ↗
35. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., and Funtowicz, M. (2020, January 16–20). Transformers: State-of-the-Art Natural Language Processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online.10.18653/v1/2020.emnlp-demos.6 ↗
36. Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing10.1145/3560815 ↗