---
title: "Generating Radiology Reports via Memory-driven Transformer"
description: "The authors use the fact that radiology reports are highly formulaic and propose a memory-driven… 39 references, cited by 62 papers here."
authors: ["Zhihong Chen", "Yan Song", "Tsung-Hui Chang", "Xiang Wan"]
year: 2020
venue: "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"
source: "https://aclanthology.org/2020.emnlp-main.112/"
doi: "10.18653/v1/2020.emnlp-main.112"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chen-2020-generating-radiology-reports-memory-driven/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2020-generating-radiology-reports-memory-driven/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/) / Generating Radiology Reports via Memory-driven Transformer

# Generating Radiology Reports via Memory-driven Transformer

**Authors:** [Zhihong Chen](https://md.research.elamur.ai/free/en/authors/zhihong-chen/), [Yan Song](https://md.research.elamur.ai/free/en/authors/yan-song/), Tsung-Hui Chang and [Xiang Wan](https://md.research.elamur.ai/free/en/authors/xiang-wan/) · **Year:** 2020 · **Venue:** [Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2020](https://md.research.elamur.ai/free/en/venues/emnlp/2020/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.emnlp-main.112/) · [PDF](https://aclanthology.org/2020.emnlp-main.112.pdf) · [DOI 10.18653/v1/2020.emnlp-main.112](https://doi.org/10.18653/v1/2020.emnlp-main.112) · [OpenAlex](https://openalex.org/W3104609094)

**Citations:** 648 citations (OpenAlex, 2026-10-14) · 62 in our library, of the 141,840 papers whose bibliographies we read

## Summary

Chest X-ray reports are long, multi-sentence texts. They usually contain a findings section and an impression section. Standard image captioning models are built for short scene descriptions and handle such reports poorly. Earlier retrieval- and template-based systems depend on large databases or hand-built template lists. The authors use the fact that radiology reports are highly formulaic and propose a memory-driven Transformer, released as R2Gen. Image patch features come from a pretrained CNN and pass through a standard Transformer encoder. A relational memory (RM) matrix in the decoder is updated at each generation step through multi-head attention, with gating and residual connections, so recurring phrasing patterns are learned implicitly. A memory-driven conditional layer normalization (MCLN) feeds the memory state into the scaling and shifting parameters of every decoder layer. On IU X-Ray and MIMIC-CXR, the model outperforms prior systems on both language generation metrics and clinical efficacy measures. Its reports are longer, cover more key medical terms, and show better image-text attention alignment. This makes automatic drafting more practical for reducing radiologists' workload.

## Key points

- Two new components: a relational memory (RM) and memory-driven conditional layer normalization (MCLN), which feeds the memory into layer-norm γ/β in the decoder. The authors describe this as the first use of memory on the decoding side of a Transformer.
- Evaluated on IU X-Ray and MIMIC-CXR. The authors claim the first published generation results on MIMIC-CXR.
- Visual features are extracted by a pretrained CNN (e.g., VGG or ResNet). Training maximizes the conditional log-likelihood of the report given the image.
- Error analysis points to class imbalance. Consolidation makes up 3.9% of MIMIC-CXR training data, and the model predicted it in 2.9% of test cases versus 6.3% in the ground truth.
- Code and the best models are available at github.com/cuhksz-nlp/R2Gen. Further analyses cover the effect of memory size.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Chinese University of Hong Kong, Shenzhen](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong-shenzhen/) — University, Shenzhen, China · 17 works · 2,364 citations
- [Shenzhen Research Institute of Big Data](https://md.research.elamur.ai/free/en/universities/shenzhen-research-institute-of-big-data/) — University, Shenzhen, China · 11 works · 1,615 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 80 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 53 works

## Cite

Cite as: Zhihong Chen, Yan Song, Tsung-Hui Chang and Xiang Wan. 2020. Generating Radiology Reports via Memory-driven Transformer. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{chen2020generating,
  title = {{Generating Radiology Reports via Memory-driven Transformer}},
  author = {Zhihong Chen, Yan Song, Tsung-Hui Chang and Xiang Wan},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2020},
  doi = {10.18653/v1/2020.emnlp-main.112},
  url = {https://doi.org/10.18653/v1/2020.emnlp-main.112}
}
```

- [← previous IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages](https://md.research.elamur.ai/free/en/papers/kakwani-2020-indicnlpsuite-monolingual-corpora-evaluation-benchmarks/)
- [next → Fact or Fiction: Verifying Scientific Claims](https://md.research.elamur.ai/free/en/papers/wadden-2020-fact-or-fiction-verifying-scientific/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/)

## References

39 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. 2018. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6077– 6086. [find](https://scholar.google.com/scholar?q=Peter+Anderson%2C+Xiaodong+He%2C+Chris+Buehler%2C+Damien+Teney%2C+Mark+Johnson%2C+Stephen+Gould%2C+and+Lei+Zhang%2E+2018%2E+Bottom%2DUp+and+Top%2DDown+Attention+for+Image+Captioning+and+Visual+Question+Answering%2E+In+Proc)
2. Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, and Charles Blundell. 2020. MEMO: A Deep Network for Flexible Combination of Episodic Memories. arXiv preprint arXiv:2001.10913. — [arXiv:2001.10913](https://arxiv.org/abs/2001.10913) [find](https://scholar.google.com/scholar?q=Andrea+Banino%2C+Adria%CC%80+Puigdome%CC%80nech+Badia%2C+Raphael+Ko%CC%88ster%2C+Martin+J+Chadwick%2C+Vinicius+Zambaldi%2C+Demis+Hassabis%2C+Caswell+Barry%2C+Matthew+Botvinick%2C+Dharshan+Kumaran%2C+and+Charles+Blundell%2E+2020%2E+MEMO%3A+)
3. Marcella Cornia, Matteo Stefanini, Lorenzo Baraldi, and Rita Cucchiara. 2019. M 2 : Meshed-Memory Transformer for Image Captioning. arXiv preprint arXiv:1912.08226. — [arXiv:1912.08226](https://arxiv.org/abs/1912.08226) [find](https://scholar.google.com/scholar?q=Marcella+Cornia%2C+Matteo+Stefanini%2C+Lorenzo+Baraldi%2C+and+Rita+Cucchiara%2E+2019%2E+M+2+%3A+Meshed%2DMemory+Transformer+for+Image+Captioning%2E+arXiv+preprint+arXiv%3A1912%2E08226%2E+%E2%80%94+%5BarXiv%3A1912%2E08226%5D%28https%3A%2F%2Farxiv%2E)
4. Dina Demner-Fushman, Marc D Kohli, Marc B Rosenman, Sonya E Shooshan, Laritza Rodriguez, Sameer Antani, George R Thoma, and Clement J McDonald. 2016. Preparing a collection of radiology examinations for distribution and retrieval. Journal of the American Medical Informatics Association, 23(2):304–31… [find](https://scholar.google.com/scholar?q=Dina+Demner%2DFushman%2C+Marc+D+Kohli%2C+Marc+B+Rosenman%2C+Sonya+E+Shooshan%2C+Laritza+Rodriguez%2C+Sameer+Antani%2C+George+R+Thoma%2C+and+Clement+J+McDonald%2E+2016%2E+Preparing+a+collection+of+radiology+examinations+f)
5. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. [find](https://scholar.google.com/scholar?q=Jia+Deng%2C+Wei+Dong%2C+Richard+Socher%2C+Li%2DJia+Li%2C+Kai+Li%2C+and+Li+Fei%2DFei%2E+2009%2E+ImageNet%3A+A+large%2Dscale+hierarchical+image+database%2E+In+2009+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+pa)
6. Michael Denkowski and Alon Lavie. 2011. [Meteor 1.3: Automatic Metric for Reliable Optimization and Evaluation of Machine Translation Systems](https://md.research.elamur.ai/free/en/papers/denkowski-2011-meteor-1-3-automatic-metric/). In Proceedings of the sixth workshop on statistical machine translation, pages 85–91.
7. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
8. Shizhe Diao, Jiaxin Bai, Yan Song, Tong Zhang, and Yonggang Wang. 2019. ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations. arXiv preprint arXiv:1911.00720. [find](https://scholar.google.com/scholar?q=Shizhe+Diao%2C+Jiaxin+Bai%2C+Yan+Song%2C+Tong+Zhang%2C+and+Yonggang+Wang%2E+2019%2E+ZEN%3A+Pre%2Dtraining+Chinese+Text+Encoder+Enhanced+by+N%2Dgram+Representations%2E+arXiv+preprint+arXiv%3A1911%2E00720%2E)
9. Shizhe Diao, Yan Song, and Tong Zhang. 2020. Keyphrase Generation with Cross-Document Attention. arXiv preprint arXiv:2004.09800. — [arXiv:2004.09800](https://arxiv.org/abs/2004.09800) [find](https://scholar.google.com/scholar?q=Shizhe+Diao%2C+Yan+Song%2C+and+Tong+Zhang%2E+2020%2E+Keyphrase+Generation+with+Cross%2DDocument+Attention%2E+arXiv+preprint+arXiv%3A2004%2E09800%2E+%E2%80%94+%5BarXiv%3A2004%2E09800%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2004%2E09800%29)
10. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. [find](https://scholar.google.com/scholar?q=Kaiming+He%2C+Xiangyu+Zhang%2C+Shaoqing+Ren%2C+and+Jian+Sun%2E+2016%2E+Deep+Residual+Learning+for+Image+Recognition%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+pages+770%E2%80%937)
11. Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, et al. 2019. CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison. In Proceedings of the AAAI Conference on Art… [find](https://scholar.google.com/scholar?q=Jeremy+Irvin%2C+Pranav+Rajpurkar%2C+Michael+Ko%2C+Yifan+Yu%2C+Silviana+Ciurea%2DIlcus%2C+Chris+Chute%2C+Henrik+Marklund%2C+Behzad+Haghgoo%2C+Robyn+Ball%2C+Katie+Shpanskaya%2C+et+al%2E+2019%2E+CheXpert%3A+A+Large+Chest+Radiograph)
12. Baoyu Jing, Zeya Wang, and Eric Xing. 2019. Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-ray Reports. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6570–6580. [find](https://scholar.google.com/scholar?q=Baoyu+Jing%2C+Zeya+Wang%2C+and+Eric+Xing%2E+2019%2E+Show%2C+Describe+and+Conclude%3A+On+Exploiting+the+Structure+Information+of+Chest+X%2Dray+Reports%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+fo)
13. Baoyu Jing, Pengtao Xie, and Eric Xing. 2018. [On the Automatic Generation of Medical Imaging Reports](https://md.research.elamur.ai/free/en/papers/jing-2018-automatic-generation-medical-imaging-reports/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2577–2586.
14. Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. 2019. MIMIC-CXR: A large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042. — [arXiv:1901.07042](https://arxiv.org/abs/1901.07042) [find](https://scholar.google.com/scholar?q=Alistair+EW+Johnson%2C+Tom+J+Pollard%2C+Seth+J+Berkowitz%2C+Nathaniel+R+Greenbaum%2C+Matthew+P+Lungren%2C+Chih%2Dying+Deng%2C+Roger+G+Mark%2C+and+Steven+Horng%2E+2019%2E+MIMIC%2DCXR%3A+A+large+publicly+available+database+of+)
15. Diederik P Kingma and Jimmy Ba. 2015. A Method for Stochastic Optimization. abs/1412.6980. [find](https://scholar.google.com/scholar?q=Diederik+P+Kingma+and+Jimmy+Ba%2E+2015%2E+A+Method+for+Stochastic+Optimization%2E+abs%2F1412%2E6980%2E)
16. Adam: CoRR, Guillaume Lample, Alexandre Sablayrolles, Marc’Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. 2019. Large Memory Layers with Product Keys. In Advances in Neural Information Processing Systems, pages 8546–8557. [find](https://scholar.google.com/scholar?q=Adam%3A+CoRR%2C+Guillaume+Lample%2C+Alexandre+Sablayrolles%2C+Marc%E2%80%99Aurelio+Ranzato%2C+Ludovic+Denoyer%2C+and+Herve%CC%81+Je%CC%81gou%2E+2019%2E+Large+Memory+Layers+with+Product+Keys%2E+In+Advances+in+Neural+Information+Processin)
17. Christy Y Li, Xiaodan Liang, Zhiting Hu, and Eric P Xing. 2019. Knowledge-Driven Encode, Retrieve, Paraphrase for Medical Image Report Generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6666–6673. [find](https://scholar.google.com/scholar?q=Christy+Y+Li%2C+Xiaodan+Liang%2C+Zhiting+Hu%2C+and+Eric+P+Xing%2E+2019%2E+Knowledge%2DDriven+Encode%2C+Retrieve%2C+Paraphrase+for+Medical+Image+Report+Generation%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+I)
18. Yuan Li, Xiaodan Liang, Zhiting Hu, and Eric P Xing. 2018. Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation. In Advances in neural information processing systems, pages 1530–1540. [find](https://scholar.google.com/scholar?q=Yuan+Li%2C+Xiaodan+Liang%2C+Zhiting+Hu%2C+and+Eric+P+Xing%2E+2018%2E+Hybrid+Retrieval%2DGeneration+Reinforced+Agent+for+Medical+Image+Report+Generation%2E+In+Advances+in+neural+information+processing+systems%2C+pages)
19. Chin-Yew Lin. 2004. [ROUGE: A Package for Automatic Evaluation of Summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81.
20. Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew Mc-Dermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, and Marzyeh Ghassemi. 2019. Clinically Accurate Chest X-Ray Report Generation. In Machine Learning for Healthcare Conference, pages 249–269. [find](https://scholar.google.com/scholar?q=Guanxiong+Liu%2C+Tzu%2DMing+Harry+Hsu%2C+Matthew+Mc%2DDermott%2C+Willie+Boag%2C+Wei%2DHung+Weng%2C+Peter+Szolovits%2C+and+Marzyeh+Ghassemi%2E+2019%2E+Clinically+Accurate+Chest+X%2DRay+Report+Generation%2E+In+Machine+Learning+f)
21. Jiasen Lu, Caiming Xiong, Devi Parikh, and Richard Socher. 2017. Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 375– 383. [find](https://scholar.google.com/scholar?q=Jiasen+Lu%2C+Caiming+Xiong%2C+Devi+Parikh%2C+and+Richard+Socher%2E+2017%2E+Knowing+When+to+Look%3A+Adaptive+Attention+via+A+Visual+Sentinel+for+Image+Captioning%2E+In+Proceedings+of+the+IEEE+conference+on+computer+)
22. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [BLEU: a Method for Automatic Evaluation of Machine Translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311–318.
23. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention Is All You Need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in neural information processing systems, pages 5998–6008.
24. Steven J Rennie, Etienne Marcheret, Youssef Mroueh, Jerret Ross, and Vaibhava Goel. 2017. [Self-critical Sequence Training for Image Captioning](https://md.research.elamur.ai/free/en/papers/rennie-2016-self-critical-sequence-training-image/). In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7008–7024.
25. Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2015. [Show and Tell: A Neural Image Caption Generator](https://md.research.elamur.ai/free/en/papers/vinyals-2014-show-tell-neural-image-caption/). In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3156–3164.
26. Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, and Timothy Lillicrap. 2018. Relational recurrent neural networks. In Advances in neural information processing systems, pages 7299–7310. [find](https://scholar.google.com/scholar?q=Adam+Santoro%2C+Ryan+Faulkner%2C+David+Raposo%2C+Jack+Rae%2C+Mike+Chrzanowski%2C+Theophane+Weber%2C+Daan+Wierstra%2C+Oriol+Vinyals%2C+Razvan+Pascanu%2C+and+Timothy+Lillicrap%2E+2018%2E+Relational+recurrent+neural+networks%2E)
27. Weixuan Wang, Zhihong Chen, and Haifeng Hu. 2019. Hierarchical Attention Network for Image Captioning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 8957–8964. [find](https://scholar.google.com/scholar?q=Weixuan+Wang%2C+Zhihong+Chen%2C+and+Haifeng+Hu%2E+2019%2E+Hierarchical+Attention+Network+for+Image+Captioning%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+33%2C+pages+8957%E2%80%938964%2E)
28. Karen Simonyan and Andrew Zisserman. 2015. [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://md.research.elamur.ai/free/en/papers/simonyan-2014-very-deep-convolutional-networks-large/). CoRR, abs/1409.1556.
29. Yan Song, Chia-Jung Lee, and Fei Xia. 2017. Learning Word Representations with Regularization from Prior Knowledge. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 143–152. [find](https://scholar.google.com/scholar?q=Yan+Song%2C+Chia%2DJung+Lee%2C+and+Fei+Xia%2E+2017%2E+Learning+Word+Representations+with+Regularization+from+Prior+Knowledge%2E+In+Proceedings+of+the+21st+Conference+on+Computational+Natural+Language+Learning+%28Co)
30. Yan Song and Shuming Shi. 2018. Complementary Learning of Word Embeddings. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pages 4368–4374. [find](https://scholar.google.com/scholar?q=Yan+Song+and+Shuming+Shi%2E+2018%2E+Complementary+Learning+of+Word+Embeddings%2E+In+Proceedings+of+the+27th+International+Joint+Conference+on+Artificial+Intelligence%2C+pages+4368%E2%80%934374%2E)
31. Sainbayar Sukhbaatar, Jason Weston, Rob Fergus, et al. 2015. End-To-End Memory Networks. In Advances in neural information processing systems, pages 2440–2448. [find](https://scholar.google.com/scholar?q=Sainbayar+Sukhbaatar%2C+Jason+Weston%2C+Rob+Fergus%2C+et+al%2E+2015%2E+End%2DTo%2DEnd+Memory+Networks%2E+In+Advances+in+neural+information+processing+systems%2C+pages+2440%E2%80%932448%2E)
32. Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, and Yonggang Wang. 2020a. Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, page… [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Yan+Song%2C+Xiang+Ao%2C+Fei+Xia%2C+Xiaojun+Quan%2C+Tong+Zhang%2C+and+Yonggang+Wang%2E+2020a%2E+Joint+Chinese+Word+Segmentation+and+Part%2Dof%2Dspeech+Tagging+via+Two%2Dway+Attentions+of+Auto%2Danalyzed+Knowled)
33. Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory Networks. CoRR, abs/1410.3916. [find](https://scholar.google.com/scholar?q=Jason+Weston%2C+Sumit+Chopra%2C+and+Antoine+Bordes%2E+2015%2E+Memory+Networks%2E+CoRR%2C+abs%2F1410%2E3916%2E)
34. Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://md.research.elamur.ai/free/en/papers/xu-2015-show-attend-tell-neural-image/). In International conference on machine learning, pages 2048–2057.
35. Jichuan Zeng, Jing Li, Yan Song, Cuiyun Gao, Michael R Lyu, and Irwin King. 2018. Topic Memory Networks for Short Text Classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3120– 3131. [find](https://scholar.google.com/scholar?q=Jichuan+Zeng%2C+Jing+Li%2C+Yan+Song%2C+Cuiyun+Gao%2C+Michael+R+Lyu%2C+and+Irwin+King%2E+2018%2E+Topic+Memory+Networks+for+Short+Text+Classification%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Nat)
36. Hongming Zhang, Jiaxin Bai, Yan Song, Kun Xu, Changlong Yu, Yangqiu Song, Wilfred Ng, and Dong Yu. 2019. Multiplex Word Embeddings for Selectional Preference Acquisition. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Confere… [find](https://scholar.google.com/scholar?q=Hongming+Zhang%2C+Jiaxin+Bai%2C+Yan+Song%2C+Kun+Xu%2C+Changlong+Yu%2C+Yangqiu+Song%2C+Wilfred+Ng%2C+and+Dong+Yu%2E+2019%2E+Multiplex+Word+Embeddings+for+Selectional+Preference+Acquisition%2E+In+Proceedings+of+the+2019+Co)
37. Yuanhe Tian, Yan Song, and Fei Xia. 2020b. Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Yan+Song%2C+and+Fei+Xia%2E+2020b%2E+Supertagging+Combinatory+Categorial+Grammar+with+Attentive+Graph+Convolutional+Networks%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natura)
38. Yuanhe Tian, Yan Song, Fei Xia, and Tong Zhang. 2020c. Improving Constituency Parsing with Span Attention. In Findings of the 2020 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Yan+Song%2C+Fei+Xia%2C+and+Tong+Zhang%2E+2020c%2E+Improving+Constituency+Parsing+with+Span+Attention%2E+In+Findings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2E)
39. Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang, and Yonggang Wang. 2020d. Improving Chinese Word Segmentation with Wordhood Memory Networks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8274–8285. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Yan+Song%2C+Fei+Xia%2C+Tong+Zhang%2C+and+Yonggang+Wang%2E+2020d%2E+Improving+Chinese+Word+Segmentation+with+Wordhood+Memory+Networks%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+fo)

*Updated 24 October 2026*