Closed-Book Training to Improve Summarization Encoder Memory
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
A good neural sequence-to-sequence summarization model should have a strong encoder that can distill and memorize the important information from long input texts so that the decoder can generate salient summaries based on the encoder's memory.In this paper, we aim to improve the memorization capabilities of the encoder of a pointer-generator model by adding an additional 'closed-book' decoder without attention and pointer mechanisms.Such a decoder forces the encoder to be more selective in the information encoded in its memory state because the decoder can't rely on the extra information provided by the attention and possibly copy modules, and hence improves the entire model.On the CNN/Daily Mail dataset, our 2-decoder model outperforms the baseline significantly in terms of ROUGE and METEOR metrics, for both cross-entropy and reinforced setups (and on human evaluation).Moreover, our model also achieves higher scores in a test-only DUC-2002 generalizability setup.We further present a memory ability test, two saliency metrics, as well as several sanity-check ablations (based on fixed-encoder, gradient-flow cut, and model capacity) to prove that the encoder of our 2-decoder model does in fact learn stronger memory representations than the baseline encoder.
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
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
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
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Bengio, S., Vinyals, O., Jaitly, N., & Shazeer, N. (2015) · arXiv · doi:10.48550/arxiv.1506.03099 · Cited by 1,621
Sequence Level Training with Recurrent Neural Networks
Ranzato, M., Chopra, S., Auli, M., & Zaremba, W. (2015) · arXiv · doi:10.48550/arxiv.1511.06732 · Cited by 1,426 · cited 2×
“Reinforced models that employ this method have achieved good results in a number of tasks including image cap-tioning (Liu et al., 2017; Ranzato et al., 2016), machine translation (Bahdanau et al., 2016; Norouzi et al., 2016), and text summarization (Ranzato et al., 2016; Paulus et al., 2018).”
MethodA Deep Reinforced Model for Abstractive Summarization
Paulus, R., Xiong, C., & Socher, R. (2017) · arXiv · doi:10.48550/arxiv.1705.04304 · Cited by 1,182
Improved Image Captioning via Policy Gradient optimization of SPIDEr
Liu, S., Zhu, Z., Ye, N., Guadarrama, S., & Murphy, K. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.100 · Cited by 430 · cited 2×
“Reinforced models that employ this method have achieved good results in a number of tasks including image cap-tioning (Liu et al., 2017; Ranzato et al., 2016), machine translation (Bahdanau et al., 2016; Norouzi et al., 2016), and text summarization (Ranzato et al., 2016; Paulus et al., 2018).”
MethodAn Actor-Critic Algorithm for Sequence Prediction
Bahdanau, D., Brakel, P., Xu, K., Goyal, A., Lowe, R., Pineau, J., Courville, A., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1607.07086 · Cited by 423
Cited by
Evaluating the Factual Consistency of Abstractive Text Summarization
Kryscinski, W., McCann, B., Xiong, C., & Socher, R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.750 · Cited by 669
SummEval: Re-evaluating Summarization Evaluation
Fabbri, A. R., Kryściński, W., McCann, B., Xiong, C., Socher, R., & Radev, D. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00373 · Cited by 587
“M15 - Closed book decoder (Jiang and Bansal, 2018) build upon a Pointer Generator Network by adding an additional copy-less and attention-less decoder during training time to force the encoder to be more selective in encoding salient content.”
Neural Text Summarization: A Critical Evaluation
Kryscinski, W., Keskar, N. S., McCann, B., Xiong, C., & Socher, R. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1051 · Cited by 335
Spurious Correlations in Reference-Free Evaluation of Text Generation
Durmus, E., Ladhak, F., & Hashimoto, T. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.102 · Cited by 16
Metadata
- Authors
- Jiang, Y., & Bansal, M.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 4067-4077
- OpenAlex
- W2891526960
- Cited by
- 34
- References
- 7
- FWCI
- 2.29
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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: Closed-Book Training to Improve Summarization Encoder Memory. https://app.cochat.ai/papers/10.18653/v1/d18-1440
- The paper
- Jiang, Y., & Bansal, M. (2018). Closed-Book Training to Improve Summarization Encoder Memory. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/d18-1440
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.