A Text Abstraction Summary Model Based on BERT Word Embedding and Reinforcement Learning
Source abstract
Abstract
As a core task of natural language processing and information retrieval, automatic text summarization is widely applied in many fields. There are two existing methods for text summarization task at present: abstractive and extractive. On this basis we propose a novel hybrid model of extractive-abstractive to combine BERT (Bidirectional Encoder Representations from Transformers) word embedding with reinforcement learning. Firstly, we convert the human-written abstractive summaries to the ground truth labels. Secondly, we use BERT word embedding as text representation and pre-train two sub-models respectively. Finally, the extraction network and the abstraction network are bridged by reinforcement learning. To verify the performance of the model, we compare it with the current popular automatic text summary model on the CNN/Daily Mail dataset, and use the ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metrics as the evaluation method. Extensive experimental results show that the accuracy of the model is improved obviously.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Natural Language Processing Techniques · Advanced Text Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Science and Engineering, Shandong Normal University, Jinan 250358, China
School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan 250357, China
References (30)
Show source-provided references
1. Cheng, J., and Lapata, M. (2016, January 7–12). Neural summarization by extracting sentences and words. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany.10.18653/v1/P16-1046 ↗
2. Nallapati, R., Zhou, B., Santos, C.N.D., Gulcehre, C., and Xiang, B. (2016, January 11–12). Abstractive text summarization using sequence-to-sequence rnns and beyond. Proceedings of the SIGNLL Conference on Computational Natural Language Learning, Berlin, Germany.10.18653/v1/K16-1028 ↗
3. Narayan, S., Cohen, S.B., and Lapata, M. (2018, January 2–4). Ranking sentences for extractive summarization with reinforcement learning. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, LA, USA.10.18653/v1/N18-1158 ↗
4. Yasunaga, M., Zhang, R., Meelu, K., Pareek, A., Srinivasan, K., and Radev, D. (2017, January 3–4). Graph-based neural multi-document summarization. Proceedings of the 21st Conference on Computational Natural Language Learning, Vancouver, BC, Canada.10.18653/v1/K17-1045 ↗
5. Rush, A.M., Chopra, S., and Weston, J. (2015, January 17–21). A neural attention model for abstractive sentence summarization. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal.10.18653/v1/D15-1044 ↗
6. 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, Vancouver, BC, Canada.
7. Paulus, R., Xiong, C., and Socher, R. (May, January 30). A deep reinforced model for abstractive summarization. Proceedings of the Sixth International Conference on Learning Representations, Vancouver, BC, Canada.
8. Li, P., Bing, L., and Lam, W. (2018). Actor-critic based training framework for abstractive summarization. arXiv.
9. Chen, Y.C., and Bansal, M. (2018, January 15–20). Fast abstractive summarization with reinforce-selected sentence rewriting. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia.10.18653/v1/P18-1063 ↗
10. Hsu, W.T., Lin, C.K., Lee, M.Y., Min, K., Tang, J., and Sun, M. (2018, January 15–20). A unified model for extractive and abstractive summarization using inconsistency loss. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia.10.18653/v1/P18-1013 ↗
11. Celikyilmaz, A., Bosselut, A., He, X., and Choi, Y. (2018, January 2–4). Deep communicating agents for abstractive summarization. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, LA, USA.10.18653/v1/N18-1150 ↗
12. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2–7). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA.
13. Sutskever, I., Vinyals, O., and Le, Q.V. (2014, January 8–13). Sequence to sequence learning with neural networks. Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
14. Cho, K., Van, M.B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25–29). Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar.10.3115/v1/D14-1179 ↗
15. Gu, J., Lu, Z., Li, H., and Li, V.O.K. (2016, January 7–12). Incorporating copying mechanism in sequence-to-sequence learning. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany.10.18653/v1/P16-1154 ↗
16. Vinyals, O., Fortunato, M., and Jaitly, N. (2015, January 7–10). Pointer networks. Proceedings of the International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
17. Sutton, R.S., and Barto, A.G. (1998). Introduction to Reinforcement Learning Cambridge, MIT Press.
18. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. Comput. Sci.
19. Lin, Z., Feng, M., Santos, C.N.D., Yu, M., Xiang, B., and Zhou, B. (2017). A Structured Self-Attentive Sentence Embedding. arXiv.
20. Li, Z., Wei, Y., Zhang, Y., and Yang, Q. (2018, January 2–7). Hierarchical attention transfer network for cross-domain sentiment classification. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.12055 ↗
21. Al-Sabahi, K., Zuping, Z., and Nadher, M. (2018). A hierarchical structured self-attentive model for extractive document summarization (hssas). IEEE Access.10.1109/ACCESS.2018.2829199 ↗
22. Nallapati, R., Zhai, F., and Zhou, B. (2017, January 4–9). Summarunner: A recurrent neural network based sequence model for extractive summarization of documents. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10958 ↗
23. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., and Gomez, A.N. (2017). Attention is all you need. Adv. Neural Inf. Process. Syst., 5998–6008.
24. Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., and Macherey, W. (2016). Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv.
25. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv.
26. Lstm: A search space odyssey10.1109/TNNLS.2016.2582924 ↗
27. Lin, C.Y. (2004, January 25–26). ROUGE: A Package for Automatic Evaluation of summaries. Proceedings of the Workshop on Text Summarization Branches Out, Barcelona, Spain.
28. Hermann, K.M., Kocisky, 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 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
29. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. Comput. Sci.
30. Zhou, Q., Yang, N., Wei, F., Huang, S., Zhou, M., and Zhao, T. (2018, January 15–20). Neural document summarization by jointly learning to score and select sentences. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia.10.18653/v1/P18-1061 ↗