Towards Improving Abstractive Summarization via Entailment Generation
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Abstractive summarization, the task of rewriting and compressing a document into a short summary, has achieved considerable success with neural sequence-tosequence models.However, these models can still benefit from stronger natural language inference skills, since a correct summary is logically entailed by the input document, i.e., it should not contain any contradictory or unrelated information.We incorporate such knowledge into an abstractive summarization model via multi-task learning, where we share its decoder parameters with those of an entailment generation model.We achieve promising initial improvements based on multiple metrics and datasets (including a test-only setting).The domain mismatch between the entailment (captions) and summarization (news) datasets suggests that the model is learning some domain-agnostic inference skills.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Get To The Point: Summarization with Pointer-Generator Networks
See, A., Liu, P. J., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1099 · Cited by 3,775
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, R., Zhou, B., dos Santos, C., Gulcehre, C., & Xiang, B. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1028 · Cited by 2,361
Microsoft COCO Captions: Data Collection and Evaluation Server
Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., & Zitnick, C. L. (2015) · arXiv · doi:10.48550/arxiv.1504.00325 · Cited by 1,614 · cited 1×
“Additionally, we also report other standard language generation metrics (as motivated recently by See et al. (2017)): METEOR (Denkowski and Lavie, 2014), BLEU-4 (Papineni et al., 2002), and CIDEr-D (Vedantam et al., 2015), based on the MS-COCO evaluation script (Chen et al., 2015).”
MethodOn Using Very Large Target Vocabulary for Neural Machine Translation
Jean, S., Cho, K., Memisevic, R., & Bengio, Y. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1001 · Cited by 862
Cited by
The Natural Language Decathlon: Multitask Learning as Question Answering
McCann, B., Keskar, N. S., Xiong, C., & Socher, R. (2018) · arXiv · doi:10.48550/arxiv.1806.08730 · Cited by 448
“Reinforcement learning has pushed performance using common summarization metrics [Paulus et al., 2017] as well as alternative metrics that transfer knowledge from another task [Pasunuru et al., 2017, Pasunuru and Bansal, 2018].”
BackgroundMethodFalke, T., Ribeiro, L. F. R., Utama, P. A., Dagan, I., & Gurevych, I. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1213 · Cited by 265
“multi-task learning with NLI (Li et al., 2018; Pasunuru et al., 2017) to successfully improve the correctness of abstractive sentence summaries.”
Abstractive Summarization: A Survey of the State of the Art
Lin, H., & Ng, V. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019815 · Cited by 120
“To address this problem, long short-term memory networks (LSTMs) (Hochreiter and Schmidhu-ber 1997) are frequently applied instead (Nema et al. 2017; Pasunuru et al. 2017; Paulus et al. 2017; See et al. 2017; Tan et al. 2017).”
BackgroundErdem, E., Kuyu, M., Yagcioglu, S., Frank, A., Parcalabescu, L., Plank, B., Babii, A., Turuta, O., Erdem, A., Calixto, I., et al. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12918 · Cited by 54
“Pasunuru et al. (2017) employed a multi-task learning setting for increasing the consistency of the summaries generated by the decoder of their neural sequence-to-sequence architecture.”
Method
Metadata
- Authors
- Pasunuru, R., Guo, H., & Bansal, M.
- Venue
- Proceedings of the Workshop on New Frontiers in Summarization
- Published
- 2017
- Pages
- 27-32
- OpenAlex
- W2757675222
- Cited by
- 33
- References
- 6
- FWCI
- 2.67
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Improving Abstractive Summarization via Entailment Generation. https://app.cochat.ai/papers/10.18653/v1/w17-4504
- The paper
- Pasunuru, R., Guo, H., & Bansal, M. (2017). Towards Improving Abstractive Summarization via Entailment Generation. Proceedings of the Workshop on New Frontiers in Summarization. https://doi.org/10.18653/v1/w17-4504
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.