---
title: "Event Extraction via Dynamic Multi-Pooling Convolutional Neural"
description: "The authors replace this pipeline with features learned automatically. 25 references, cited by 269 papers here."
authors: ["Yubo Chen", "Liheng Xu", "Kang Liu", "Daojian Zeng", "Jun Zhao"]
year: 2015
venue: "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)"
source: "https://aclanthology.org/P15-1017/"
doi: "10.3115/v1/p15-1017"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chen-2015-event-extraction-dynamic-multi-pooling/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2015-event-extraction-dynamic-multi-pooling/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/) / Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks

# Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks

**Authors:** [Yubo Chen](https://md.research.elamur.ai/free/en/authors/yubo-chen/), [Liheng Xu](https://md.research.elamur.ai/free/en/authors/liheng-xu/), [Kang Liu](https://md.research.elamur.ai/free/en/authors/kang-liu/), [Daojian Zeng](https://md.research.elamur.ai/free/en/authors/daojian-zeng/) and [Jun Zhao](https://md.research.elamur.ai/free/en/authors/jun-zhao/) · **Year:** 2015 · **Venue:** [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)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2015](https://md.research.elamur.ai/free/en/venues/acl/2015/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P15-1017/) · [PDF](https://aclanthology.org/P15-1017.pdf) · [DOI 10.3115/v1/p15-1017](https://doi.org/10.3115/v1/p15-1017) · [OpenAlex](https://openalex.org/W2250999640)

**Citations:** 906 citations (OpenAlex, 2026-10-14) · [269](https://md.research.elamur.ai/free/en/papers/chen-2015-event-extraction-dynamic-multi-pooling/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper addresses ACE event extraction: finding trigger words, assigning their event subtypes, and attaching arguments with roles. Earlier systems relied on hand-crafted features and on outputs from parsers and other NLP tools. That approach costs a lot of human effort, suffers from sparse one-hot features, and lets upstream errors propagate. The authors replace this pipeline with features learned automatically.

- **Lexical-level clues:** Skip-gram word embeddings of the candidate words and their immediate neighbours.
- **Sentence-level clues:** a convolutional network with a new dynamic multi-pooling layer. Instead of taking one maximum over the whole sentence, it splits the sentence at the trigger and the candidate argument and max-pools each segment separately.

The resulting model, DMCNN, is applied in two stages: trigger classification, then argument classification. On the ACE2005 dataset it reportedly beats prior state-of-the-art feature-based and structure-based systems. This matters because roughly a quarter of the sentences describe several events, and ordinary max-pooling tends to discard the information needed for the less dominant event.

## Key points
- Multiple-event sentences make up 27.3% of the dataset. This is the main motivation for pooling per segment rather than once per sentence.
- The task follows the ACE definitions: 8 event types and 33 subtypes, with gold entity labels from ACE used directly, as in most earlier work.
- The sentence-level input combines three parts:
  - context-word features (CWF);
  - position features (PF), which are learned embeddings of relative distance to the trigger or candidate argument;
  - an event-type feature (EF) for the argument stage.
- Ablation (Table 5) shows the two feature groups are complementary:

  | Features used | Trigger F1 | Argument F1 |
  |---|---|---|
  | Lexical only | 64.9 | 40.2 |
  | Sentence-level only | 63.8 | 50.7 |
  | Combined | 69.1 | 53.5 |

- Many test items are unseen in training with the same label: 34.9% of trigger words and 83.1% of arguments. In the unseen case, embedding-based lexical features beat discrete baseline features by 18.8% for triggers and 8.5% for arguments.

## Interesting ideas
- **Pooling split at task-relevant anchors:** cutting a sequence at key positions (trigger, argument) and pooling each piece keeps local evidence that a single global max would throw away. This could carry over to relation extraction or any task where a sentence holds several competing signals.
- **Learned relative-distance embeddings:** encoding each token's offset from the words being classified tells a CNN which items are in focus without any parser. This is a cheap trick for tasks centred on spans or entities.
- **Two-stage pipeline with shared architecture:** detect triggers first, then reuse a similar network, conditioned on the predicted event type, to classify arguments. This keeps the model design uniform while letting the second stage use first-stage output.
- **Evaluating seen vs. unseen items separately:** splitting test triggers and arguments by whether they occurred in training with the same label shows where dense features actually help. This is a useful diagnostic for low-resource or sparse-label settings.
- **Ablating lexical vs. sentence features:** comparing each feature group alone and combined shows which one drives each subtask. Here sentence context mattered much more for arguments than for triggers.

*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 Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 68 works · 22,753 citations
- [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 20 works · 13,875 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works

🧭 Topics (1): [🔎 Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/) · 109 works

## Appears in

Agglomerations: [🏙️ Beijing](https://md.research.elamur.ai/free/en/agglomerations/beijing/)

## Cite

Cite as: Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng and Jun Zhao. 2015. Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks. 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).

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

```bibtex
@inproceedings{chen2015event,
  title = {{Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks}},
  author = {Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng and Jun Zhao},
  booktitle = {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)},
  year = {2015},
  doi = {10.3115/v1/p15-1017},
  url = {https://doi.org/10.3115/v1/p15-1017}
}
```

- [← previous Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://md.research.elamur.ai/free/en/papers/wen-2015-semantically-conditioned-lstm-based-natural/)
- [next → WikiQA: A Challenge Dataset for Open-Domain Question Answering](https://md.research.elamur.ai/free/en/papers/yang-2015-wikiqa-challenge-dataset-open-domain/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/)

## References

25 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. David Ahn. 2006. [The stages of event extraction](https://md.research.elamur.ai/free/en/papers/ahn-2006-stages-event-extraction/). In Proceedings of ACL, pages 1–8.
2. Marco Baroni, Georgiana Dinu, and Germán Kruszewski. 2014. [Dont count, predict!](https://md.research.elamur.ai/free/en/papers/baroni-2014-don-t-count-predict-systematic/) a systematic comparison of context-counting vs. context-predicting semantic vectors. In Proceedings of ACL, pages 238–247.
3. Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Jauvin. 2003. [A neural probabilistic language model](https://md.research.elamur.ai/free/en/papers/bengio-2003-neural-probabilistic-language-model/). The Journal of Machine Learning Research, 3:1137–1155.
4. Chen Chen and V Incent NG. 2012. Joint modeling for chinese event extraction with rich linguistic features. In Proceedings of COLING, pages 529–544. [find](https://scholar.google.com/scholar?q=Chen+Chen+and+V+Incent+NG%2E+2012%2E+Joint+modeling+for+chinese+event+extraction+with+rich+linguistic+features%2E+In+Proceedings+of+COLING%2C+pages+529%E2%80%93544%2E)
5. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. [Natural language processing (almost) from scratch](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/). The Journal of Machine Learning Research, 12:2493–2537.
6. Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. 2010. Why does unsupervised pre-training help deep learning? The Journal of Machine Learning Research, 11:625–660. [find](https://scholar.google.com/scholar?q=Dumitru+Erhan%2C+Yoshua+Bengio%2C+Aaron+Courville%2C+Pierre%2DAntoine+Manzagol%2C+Pascal+Vincent%2C+and+Samy+Bengio%2E+2010%2E+Why+does+unsupervised+pre%2Dtraining+help+deep+learning%3F+The+Journal+of+Machine+Learning+Re)
7. Prashant Gupta and Heng Ji. 2009. Predicting unknown time arguments based on cross-event propagation. In Proceedings of ACL-IJCNLP, pages 369– 372. [find](https://scholar.google.com/scholar?q=Prashant+Gupta+and+Heng+Ji%2E+2009%2E+Predicting+unknown+time+arguments+based+on+cross%2Devent+propagation%2E+In+Proceedings+of+ACL%2DIJCNLP%2C+pages+369%E2%80%93+372%2E)
8. Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. 2012. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580. [find](https://scholar.google.com/scholar?q=Geoffrey+E+Hinton%2C+Nitish+Srivastava%2C+Alex+Krizhevsky%2C+Ilya+Sutskever%2C+and+Ruslan+R+Salakhutdinov%2E+2012%2E+Improving+neural+networks+by+preventing+co%2Dadaptation+of+feature+detectors%2E+arXiv+preprint+arXi)
9. Yu Hong, Jianfeng Zhang, Bin Ma, Jianmin Yao, Guodong Zhou, and Qiaoming Zhu. 2011. [Using cross-entity inference to improve event extraction](https://md.research.elamur.ai/free/en/papers/hong-2011-cross-entity-inference-improve-event/). In Proceedings of ACL-HLT, pages 1127–1136.
10. Heng Ji and Ralph Grishman. 2008. [Refining event extraction through cross-document inference](https://md.research.elamur.ai/free/en/papers/ji-2008-refining-event-extraction-through-cross/). In Proceedings of ACL, pages 254–262.
11. Nal Kalchbrenner and Phil Blunsom. 2013. [Recurrent convolutional neural networks for discourse compositionality](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-convolutional-neural-networks-discourse/). arXiv preprint arXiv:1306.3584.
12. Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. [A convolutional neural network for modelling sentences](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2014-convolutional-neural-network-modelling-sentences/). arXiv preprint arXiv:1404.2188.
13. Yoon Kim. 2014. [Convolutional neural networks for sentence classification](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/). arXiv preprint arXiv:1408.5882.
14. Siwei Lai, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Recurrent convolutional neural networks for text classification. In Proceedings of AAAI. [find](https://scholar.google.com/scholar?q=Siwei+Lai%2C+Liheng+Xu%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2015%2E+Recurrent+convolutional+neural+networks+for+text+classification%2E+In+Proceedings+of+AAAI%2E)
15. Qi Li, Heng Ji, and Liang Huang. 2013. [Joint event extraction via structured prediction with global features](https://md.research.elamur.ai/free/en/papers/li-2013-joint-event-extraction-structured-prediction/). In Proceedings of ACL, pages 73–82.
16. Qi Li, Heng Ji, Yu Hong, and Sujian Li. 2014. Constructing information networks using one single model. In Proceedings of EMNLP, pages 1846– 1851. [find](https://scholar.google.com/scholar?q=Qi+Li%2C+Heng+Ji%2C+Yu+Hong%2C+and+Sujian+Li%2E+2014%2E+Constructing+information+networks+using+one+single+model%2E+In+Proceedings+of+EMNLP%2C+pages+1846%E2%80%93+1851%2E)
17. Shasha Liao and Ralph Grishman. 2010. [Using document level cross-event inference to improve event extraction](https://md.research.elamur.ai/free/en/papers/liao-2010-document-level-cross-event-inference/). In Proceedings of ACL, pages 789–797.
18. David McClosky, Mihai Surdeanu, and Christopher D Manning. 2011. [Event extraction as dependency parsing](https://md.research.elamur.ai/free/en/papers/mcclosky-2011-event-extraction-as-dependency-parsing/). In Proceedings of ACL-HLT, pages 1626– 1635.
19. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. [Efficient estimation of word representations in vector space](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/). arXiv preprint arXiv:1301.3781.
20. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013b. [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Proceedings of NIPS, pages 3111–3119.
21. Frederic Morin and Yoshua Bengio. 2005. Hierarchical probabilistic neural network language model. In Proceedings of AISTATS, pages 246–252. [find](https://scholar.google.com/scholar?q=Frederic+Morin+and+Yoshua+Bengio%2E+2005%2E+Hierarchical+probabilistic+neural+network+language+model%2E+In+Proceedings+of+AISTATS%2C+pages+246%E2%80%93252%2E)
22. Joseph Turian, Lev Ratinov, and Yoshua Bengio. 2010. [Word representations: a simple and general method for semi-supervised learning](https://md.research.elamur.ai/free/en/papers/turian-2010-word-representations-simple-general-method/). In Proceedings of ACL, pages 384–394.
23. David Yarowsky. 1995. [Unsupervised word sense disambiguation rivaling supervised methods](https://md.research.elamur.ai/free/en/papers/yarowsky-1995-unsupervised-word-sense-disambiguation-rivaling/). In Proceedings of ACL, pages 189–196.
24. Matthew D Zeiler. 2012. [Adadelta: An adaptive learning rate method](https://md.research.elamur.ai/free/en/papers/zeiler-2012-adadelta-adaptive-learning-rate-method/). arXiv preprint arXiv:1212.5701.
25. Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. 2014. [Relation classification via convolutional deep neural network](https://md.research.elamur.ai/free/en/papers/zeng-2014-relation-classification-convolutional-deep-neural/). In Proceedings of COLING, pages 2335–2344.

*Updated 24 October 2026*