Neural Text Summarization Piji Li NLP Center, Tencent AI Lab - - PowerPoint PPT Presentation
Neural Text Summarization Piji Li NLP Center, Tencent AI Lab pijili@tencent.com Paper Reading, Sep.6, 2018 Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 1 / 63 Table of Contents Introduction 1 Methods 2 Conclusion 3
Piji Li
NLP Center, Tencent AI Lab pijili@tencent.com
Paper Reading, Sep.6, 2018
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 1 / 63
1
Introduction
2
Methods
3
Conclusion
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 2 / 63
1
Introduction
2
Methods
3
Conclusion
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 3 / 63
Text Summarization
The goal of automatic text summarization is to automatically produce a succinct summary, preserving the most important information for a single document or a set of documents about the same topic (event).
7/11/2017 mogren.one/graphics/illustrations/mogren_summarization.svg http://mogren.one/graphics/illustrations/mogren_summarization.svg 1/1
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 4 / 63
Text Summarization - Categories
Input:
Single-Document Summarization (SDS) Multi-Document Summarization (MDS)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 5 / 63
Single-Document Summarization
Cambodian leader Hun Sen on Friday rejected opposition parties ' demands for talks outside the country , accusing them of trying to `` internationalize '' the political crisis . Government and opposition parties have asked King Norodom Sihanouk to host a summit meeting after a series of post-election negotiations between the two opposition groups and Hun Sen 's party to form a new government failed . Opposition leaders Prince Norodom Ranariddh and Sam Rainsy , citing Hun Sen 's threats to arrest opposition figures after two alleged attempts
for talks at Sihanouk 's residence in Beijing .Hun Sen , however , rejected that .`` I would like to make it clear that all meetings related to Cambodian affairs must be conducted in the Kingdom of Cambodia , '' Hun Sen told reporters after a Cabinet meeting on Friday .`` No-one should internationalize Cambodian affairs . It is detrimental to the sovereignty of Cambodia , '' he said .Hun Sen 's Cambodian People 's Party won 64 of the 122 parliamentary seats in July 's elections , short of the two-thirds majority needed to form a government on its own .Ranariddh and Sam Rainsy have charged that Hun Sen 's victory in the elections was achieved through widespread fraud .They have demanded a thorough investigation into their election complaints as a precondition for their cooperation in getting the national assembly moving and a new government formed …….
Cambodian government rejects
Document Summary
Figure 1: Single-document summarization.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 6 / 63
Multi-Document Summarization
Fingerprints and photos of two men who boarded the doomed Malaysia Airlines passenger jet are being sent to U.S. authorities so they can be compared against records of known terrorists and
that they believed that terrorism was involved, but they are also not ruling anything out. The investigation into the disappearance of the jetliner with 239 passengers and crew has centered so far around the fact that two passengers used passports stolen in Thailand from an Austrian and an
passengers, one adult and two children, were American. …… (CNN) -- A delegation of painters and calligraphers, a group of Buddhists returning from a religious gathering in Kuala Lumpur, a three-generation family, nine senior travelers and five
according to the airline's flight manifest. The 12 missing crew members on the flight that disappeared early Saturday were Malaysian. The airline's list showed the passengers hailed from 14 countries, but later it was learned that two people named on the manifest -- an Austrian and an Italian -- whose passports had been stolen were not aboard the plane. The plane was carrying five children under 5 years old, the airline said. …… Vietnamese aircraft spotted what they suspected was one of the doors belonging to the ill-fated Malaysia Airlines Flight MH370 on Sunday, as troubling questions emerged about how two passengers managed to board the Boeing 777 using stolen passports. The discovery comes as
The state-run Thanh Nien newspaper cited Lt. Gen. Vo Van Tuan, deputy chief of staff of Vietnam's army, as saying searchers in a low-flying plane had spotted an object suspected of being a door from the missing jet. It was found in waters about 56 miles south of Tho Chu island, in the same area where oil slicks were spotted Saturday. ……
…
Flight MH370, carrying 239 people vanished
the South China Sea in less than an hour after taking off from Kuala Lumpur, with two passengers boarded the Boeing 777 using stolen passports. Possible reasons could be an abrupt breakup of the plane
an act
terrorism. The government was determining the "true identities" of the passengers who used the stolen passports. Investigators were trying to determine the path
plane by analysing civilian and military radar data while ships and aircraft from seven countries scouring the seas around Malaysia and south of Vietnam. Documents Summary
Figure 2: Multi-document summarization for the topic “Malaysia Airlines Disappearance”.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 7 / 63
Text Summarization - Categories
Input:
Single-Document Summarization (SDS) Multi-Document Summarization (MDS)
Output:
Extractive Compressive Abstractive
Machine learning methods:
Supervised Unsupervised
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 8 / 63
Text Summarization - History
Since 1950s:
Concept Weight (Luhn, 1958), Centroid (Radev et al., 2004), LexRank (Erkan and Radev, 2004), TextRank (Mihalcea and Tarau, 2004), Sparse Coding (He et al., 2012; Li et al., 2015) Feature+Regression (Min et al., 2012; Wang et al., 2013)
Most of the summarization methods are extractive. Abstractive summarization is full of challenges. Some indirect methods employ sentence fusing (Barzilay and McKeown, 2005) or phrase merging (Bing et al., 2015). The indirect strategies will do harm to the linguistic quality of the constructed sentences.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 9 / 63
Text Summarization - History
Before the neural summarization era...silent 2012 2015 (Rush et al., 2015)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 10 / 63
1
Introduction
2
Methods
3
Conclusion
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 11 / 63
Essential Idea
Salience Detection (Words, Sentences)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 12 / 63
Inspiration from DBN, DNN, CNN
Liu, Yan, Sheng-hua Zhong, and Wenjie Li. “Query-Oriented Multi-Document Summarization via Unsupervised Deep Learn- ing.” In AAAI. 2012. Denil, Misha, Alban Demiraj, Nal Kalchbrenner, Phil Blunsom, and Nando de Freitas. “Modelling, visualising and summarising doc- uments with a single convolu- tional neural network.” arXiv preprint arXiv:1406.3830 (2014).
Figure 3: Visualization of Parameters.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 13 / 63
Better Semantic Representations
Since 1950s:
Concept Weight (Luhn, 1958), Centroid (Radev et al., 2004), LexRank (Erkan and Radev, 2004), TextRank (Mihalcea and Tarau, 2004), Sparse Coding (He et al., 2012; Li et al., 2015)
Bag-of-Words (BoWs)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 14 / 63
Better Semantic Representations
Word2vec (Mikolov et al., 2013), Paragraph Vector (Le and Mikolov, 2014), RNN-Sent (Tang et al., 2015), CNN-Sent (Kim, 2014) Improve the performance of PageRank and Data Reconstruction based models. Works:
K˚ ageb¨ ack, Mikael, Olof Mogren, Nina Tahmasebi, and Devdatt Dub-
models.” In CVSC 2014. Yin, Wenpeng, and Yulong Pei. ”Optimizing Sentence Modeling and Selection for Document Summarization.” In IJCAI 2015. Li, Piji, Wai Lam, Lidong Bing, Weiwei Guo, and Hang Li. ”Cascaded attention based unsupervised information distillation for compres- sive summarization.” In EMNLP 2017.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 15 / 63
Inspiration from NMT
Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio. ”Neural machine translation by jointly learning to align and translate.” arXiv preprint arXiv:1409.0473 (2014). (citation:4300+)
Figure 4: Attention-based seq2seq framework. Figure from OpenNMT (Klein et al., 2017)
.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 16 / 63
2015
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 17 / 63
A Neural Attention Model for Abstractive Sentence Summarization
Rush, Alexander M., Sumit Chopra, and Jason Weston. ”A neural attention model for abstractive sentence summarization.” EMNLP (2015). (citation:570+)
Figure 5: (a) NNLM decoder with additional encoder element. (b) Attention based encoder.
.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 18 / 63
A Neural Attention Model for Abstractive Sentence Summarization
Rush, Alexander M., Sumit Chopra, and Jason Weston. ”A neural attention model for abstractive sentence summarization.” EMNLP (2015). (citation:570+)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 19 / 63
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
Hu, Baotian, Qingcai Chen, and Fangze Zhu. ”LCSTS: A Large Scale Chinese Short Text Summarization Dataset.” EMNLP (2015). (citation:49)
（a） （b）
Figure 6: (a) Encoder-Decoder. (b) Attention based Decoder.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 20 / 63
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
Hu, Baotian, Qingcai Chen, and Fangze Zhu. ”LCSTS: A Large Scale Chinese Short Text Summarization Dataset.” EMNLP (2015). (citation:49)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 21 / 63
Generating News Headlines with Recurrent Neural Networks
Lopyrev, Konstantin. ”Generating news headlines with recurrent neural networks.” arXiv preprint arXiv:1512.01712 (2015). (citation:28) Investigations of several NMT models.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 22 / 63
2016
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 23 / 63
Abstractive sentence summarization with attentive recurrent neural networks
Chopra, Sumit, Michael Auli, and Alexander M. Rush. ”Abstractive sentence summarization with attentive recurrent neural networks.” NAACL, pp. 93-98. 2016. (citation:138)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 24 / 63
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, Ramesh, Bowen Zhou, Cicero dos Santos, C ¸a glar Gul¸ cehre, and Bing Xiang. ”Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond.” CoNLL 2016 (2016):
3 pages version in Feb. 2016. Many tricks (nmt, copy, coverage, hierarchical, external knowledge).
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 25 / 63
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, Ramesh, Bowen Zhou, Cicero dos Santos, C ¸a glar Gul¸ cehre, and Bing Xiang. ”Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond.” CoNLL 2016 (2016):
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 26 / 63
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, Ramesh, Bowen Zhou, Cicero dos Santos, C ¸a glar Gul¸ cehre, and Bing Xiang. ”Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond.” CoNLL 2016 (2016):
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 27 / 63
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, Ramesh, Bowen Zhou, Cicero dos Santos, C ¸a glar Gul¸ cehre, and Bing Xiang. ”Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond.” CoNLL 2016 (2016):
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 28 / 63
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, Ramesh, Bowen Zhou, Cicero dos Santos, C ¸a glar Gul¸ cehre, and Bing Xiang. ”Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond.” CoNLL 2016 (2016):
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 29 / 63
Why Copy?
OOV Extraction
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 30 / 63
Copy Mechanism
Vinyals, Oriol, Meire Fortunato, and Navdeep Jaitly. ”Pointer networks.” In NIPS, pp. 2692-2700. 2015. (citation:352) Gulcehre, Caglar, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. ”Pointing the Unknown Words.” In ACL, vol. 1,
Gu, Jiatao, Zhengdong Lu, Hang Li, and Victor OK Li. ”Incorporating Copying Mechanism in Sequence-to-Sequence Learning.” In ACL, vol. 1, pp. 1631-1640. 2016. (citation:192)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 31 / 63
Copy Mechanism
Figure 7: Pointer-generator model. (See et al., 2017)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 32 / 63
Copy Mechanism – Performance
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 33 / 63
Why Coverage?
Diversity
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 34 / 63
Coverage Mechanism
Tu, Zhaopeng, Zhengdong Lu, Yang Liu, Xiaohua Liu, and Hang Li. ”Modeling Coverage for Neural Machine Translation.” In ACL 2016. (citation:187) Chen, Qian, Xiaodan Zhu, Zhenhua Ling, Si Wei, and Hui Jiang. ”Distraction-based neural networks for modeling documents.” In IJCAI 2016. (citation:28)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 35 / 63
Coverage Mechanism
Chen, Qian, Xiaodan Zhu, Zhenhua Ling, Si Wei, and Hui Jiang. ”Distraction-based neural networks for modeling documents.” In IJCAI 2016. (citation:28)
Figure 8: Operation of coverage mechanism.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 36 / 63
Coverage Mechanism – Performance
Chen, Qian, Xiaodan Zhu, Zhenhua Ling, Si Wei, and Hui Jiang. ”Distraction-based neural networks for modeling documents.” In IJCAI 2016. (citation:28)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 37 / 63
More Works in 20161
Cheng, Jianpeng, and Mirella Lapata. ”Neural Summarization by Extracting Sentences and Words.” In ACL, 2016. (citation:108) Cao, Ziqiang, Wenjie Li, Sujian Li, Furu Wei, and Yanran Li. ”AttSum: Joint Learning of Focusing and Summarization with Neural Attention.” In COLING, 2016. Zeng, Wenyuan, Wenjie Luo, Sanja Fidler, and Raquel Urtasun. ”Efficient summarization with read-again and copy mechanism.” arXiv preprint arXiv:1611.03382 (2016). Miao, Yishu, and Phil Blunsom. ”Language as a Latent Variable: Discrete Generative Models for Sentence Compression.” In EMNLP. 2016. ...
1https://github.com/lipiji/App-DL#text-summarization Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 38 / 63
2017
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 39 / 63
Inspirations from the traditional summarization methods.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 40 / 63
Nallapati, Ramesh, Feifei Zhai, and Bowen Zhou. ”SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents.” In AAAI, pp. 3075-3081. 2017. (citation:58)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 41 / 63
Abstractive document summarization with a graph-based attentional neural model
Tan, Jiwei, Xiaojun Wan, and Jianguo Xiao. ”Abstractive document summarization with a graph-based attentional neural model.” In ACL 2017. (citation:24) ACL Outstanding Paper.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 42 / 63
Abstractive document summarization with a graph-based attentional neural model
Tan, Jiwei, Xiaojun Wan, and Jianguo Xiao. ”Abstractive document summarization with a graph-based attentional neural model.” In ACL 2017. (citation:24)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 43 / 63
Selective Encoding for Abstractive Sentence Summarization
Zhou, Qingyu, Nan Yang, Furu Wei, and Ming Zhou. ”Selective Encoding for Abstractive Sentence Summarization.” In ACL
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 44 / 63
Recall the Copy and Coverage Mechanism in 2016.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 45 / 63
Selective Encoding for Abstractive Sentence Summarization
See, Abigail, Peter J. Liu, and Christopher D. Manning. ”Get To The Point: Summarization with Pointer-Generator Networks.” In ACL 2017. (citation:114) Writing? Figures?
Figure 9: Pointer-Generator Networks.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 46 / 63
Reinforcement Learning.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 47 / 63
A deep reinforced model for abstractive summarization
Paulus, Romain, Caiming Xiong, and Richard Socher. ”A deep reinforced model for abstractive summarization.” arXiv preprint arXiv:1705.04304 (2017). (citation:107)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 48 / 63
A deep reinforced model for abstractive summarization
Intra-attention modeling. Reinforced learning trick.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 49 / 63
A deep reinforced model for abstractive summarization
Paulus, Romain, Caiming Xiong, and Richard Socher. ”A deep reinforced model for abstractive summarization.” arXiv preprint arXiv:1705.04304 (2017). (citation:107)
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 50 / 63
2018
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 51 / 63
Reinforcement Learning based Methods
Celikyilmaz, Asli, Antoine Bosselut, Xiaodong He, and Yejin Choi. ”Deep Communicating Agents for Abstractive Summarization.” In NAACL 2018. Wu, Yuxiang, and Baotian Hu. ”Learning to Extract Coherent Summary via Deep Reinforcement Learning.” In AAAI 2018. Wang, Li, Junlin Yao, Yunzhe Tao, Li Zhong, Wei Liu, and Qiang Du. ”A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization.” In IJCAI 2018. Chen, Yen-Chun, and Mohit Bansal. ”Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting.” arXiv preprint arXiv:1805.11080 (2018). Keneshloo, Yaser, Tian Shi, Chandan K. Reddy, and Naren
Sequence Models.” arXiv preprint arXiv:1805.09461 (2018).
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 52 / 63
CNN-seq2seq, Transformer
Wang, Li, Junlin Yao, Yunzhe Tao, Li Zhong, Wei Liu, and Qiang Du. ”A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization.” In IJCAI 2018.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 53 / 63
Recent Works
Wojciech Kry´ sci´ nski, Romain Paulus, Caiming Xiong, Richard Socher. ”Improving Abstraction in Text Summarization .” arXiv preprint arXiv:1808.07913 (2018). Zhang, Xingxing, Mirella Lapata, Furu Wei, and Ming Zhou. ”Neural Latent Extractive Document Summarization.” arXiv preprint arXiv:1808.07187 (2018). Sebastian Gehrmann, Yuntian Deng, Alexander M. Rush. ”Bottom-Up Abstractive Summarization.” arXiv preprint arXiv:1808.10792 (2018).
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 54 / 63
More: https://github.com/lipiji/App-DL#text-summarization
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 55 / 63
1
Introduction
2
Methods
3
Conclusion
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 56 / 63
Challenges:
Long text abstractive summarization. Abstractive multi-document summarization.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 57 / 63
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 58 / 63
Regina Barzilay and Kathleen R McKeown. Sentence fusion for multi- document news summarization. Computational Linguistics, 31(3):297– 328, 2005. Lidong Bing, Piji Li, Yi Liao, Wai Lam, Weiwei Guo, and Rebecca Passon-
for Computational Linguistics and the 7th International Joint Conference
pages 1587–1597, 2015. G¨ unes Erkan and Dragomir R Radev. Lexrank: Graph-based lexical cen- trality as salience in text summarization. Journal of Artificial Intelligence Research, 22:457–479, 2004.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 59 / 63
Zhanying He, Chun Chen, Jiajun Bu, Can Wang, Lijun Zhang, Deng Cai, and Xiaofei He. Document summarization based on data reconstruction. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intel- ligence, pages 620–626. AAAI Press, 2012. Yoon Kim. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1746–1751, 2014. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M Rush. Opennmt: Open-source toolkit for neural machine translation. arXiv preprint arXiv:1701.02810, 2017. Quoc Le and Tomas Mikolov. Distributed representations of sentences and documents. In International Conference on Machine Learning, pages 1188–1196, 2014.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 60 / 63
Piji Li, Lidong Bing, Wai Lam, Hang Li, and Yi Liao. Reader-aware multi- document summarization via sparse coding. In The 24th International Joint Conference on Artificial Intelligence, pages 1270–1276, 2015. Hans Peter Luhn. The automatic creation of literature abstracts. IBM Journal of research and development, 2(2):159–165, 1958. Rada Mihalcea and Paul Tarau. Textrank: Bringing order into text. In Pro- ceedings of the 2004 conference on empirical methods in natural language processing, 2004. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013. Ziheng Lin Min, Yen Kan Chew, and Lim Tan. Exploiting category-specific information for multi-document summarization. The 21th International Conference on Computational Linguistics (COLING), pages 2903–2108, 2012.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 61 / 63
Dragomir R Radev, Hongyan Jing, Ma lgorzata Sty´ s, and Daniel Tam. Centroid-based summarization of multiple documents. Information Pro- cessing & Management, 40(6):919–938, 2004. Alexander M Rush, Sumit Chopra, and Jason Weston. A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 379–389, 2015. Abigail See, Peter J Liu, and Christopher D Manning. Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 1073–1083, 2017. Duyu Tang, Bing Qin, and Ting Liu. Document modeling with gated re- current neural network for sentiment classification. In Proceedings of the 2015 conference on empirical methods in natural language processing, pages 1422–1432, 2015.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 62 / 63
Lu Wang, Hema Raghavan, Vittorio Castelli, Radu Florian, and Claire
document summarization. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 1384–1394, 2013.
Piji Li (Tencent AI Lab) Neural Text Summarization Sep.6, 2018 63 / 63