---
title: "Neural Open Information Extraction — paper by Cui et al. (2018)"
description: "Cui, Wei and Zhou replace this pipeline with an end-to-end neural model that treats binary Open IE as… 31 references, cited by 55 papers here."
authors: ["Lei Cui", "Furu Wei", "Ming Zhou"]
year: 2018
venue: "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"
source: "https://aclanthology.org/P18-2065/"
doi: "10.18653/v1/p18-2065"
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/cui-2018-neural-open-information-extraction/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/cui-2018-neural-open-information-extraction/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/) / Neural Open Information Extraction

# Neural Open Information Extraction

**Authors:** [Lei Cui](https://md.research.elamur.ai/free/en/authors/lei-cui/), [Furu Wei](https://md.research.elamur.ai/free/en/authors/furu-wei/) and [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/) · **Year:** 2018 · **Venue:** [Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2018](https://md.research.elamur.ai/free/en/venues/acl/2018/)) · **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/P18-2065/) · [PDF](https://aclanthology.org/P18-2065.pdf) · [DOI 10.18653/v1/p18-2065](https://doi.org/10.18653/v1/p18-2065) · [OpenAlex](https://openalex.org/W2897509371)

**Citations:** 133 citations (OpenAlex, 2026-10-14) · [55](https://md.research.elamur.ai/free/en/papers/cui-2018-neural-open-information-extraction/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Most Open IE systems derive relation tuples from hand-written patterns applied to syntactic parser output. Errors from those upstream tools carry into the final extractions and accumulate. Cui, Wei and Zhou replace this pipeline with an end-to-end neural model that treats binary Open IE as sequence-to-sequence generation. The model reads a sentence and outputs its tuples as a single token sequence, with placeholder tags marking arg1, the relation and arg2.

The architecture is an LSTM encoder-decoder with attention and a copying mechanism, so that arguments and relations are taken directly from spans of the input. Training data was not annotated by hand. Instead, the authors ran OpenIE4 over Wikipedia and kept only its most confident extractions.

On a large public benchmark, the model achieved the best area under the precision-recall curve among the systems tested. It surpassed OpenIE4 itself, even though it rarely reproduces that system's exact outputs, and it was notably better at finding argument boundaries in long sentences. Its speed on a GPU was similar to conventional systems. The work matters because it shows Open IE can drop parser dependencies, and it releases a large silver-standard training corpus.

## Key points
- **Training data:** The training corpus was built from the Wikipedia dump 20,180,101, using sentences of 40 words or fewer.
  - OpenIE4 binary tuples with confidence ≥ 0.9 were kept.
  - This yielded 36,247,584 sentence–tuple pairs, which were publicly released.
- **Model:** The model was built in OpenNMT.
  - It uses a 3-layer bidirectional LSTM encoder and a 3-layer LSTM decoder.
  - Hidden states and embeddings are 256-dimensional, with a 50k vocabulary.
  - It adds Bahdanau-style attention and a simplified copying mechanism adapted from See et al.
  - Training took 3 days on 4 M60 GPUs.
- **Evaluation setup:** The test set was the Stanovsky and Dagan (2016) benchmark, with 3,200 sentences and 10,359 gold extractions.
  - Baselines were OLLIE, ClausIE, Stanford OPENIE, PropS and OPENIE4.
- **Accuracy:** With top-5 outputs, the neural system reached the highest AUC, 0.473.
  - Only 11.4% of its extractions match OpenIE4's, which suggests the model generalizes rather than copies its teacher.
- **Speed:** On the 3,200 test sentences, the neural system took 172 s on an M60 GPU.
  - On a Xeon 2.4 GHz CPU, the baselines took 160 s (Ollie), 181 s (OpenIE4), 234 s (Stanford), 432 s (PropS) and 960 s (ClausIE).

*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

- [Microsoft Research Asia](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) — Company, Beijing, China · 54 works · 59,921 citations

📚 Shelves (4): [🖥️ 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

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

## Cite

Cite as: Lei Cui, Furu Wei and Ming Zhou. 2018. Neural Open Information Extraction. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).

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

```bibtex
@inproceedings{cui2018neural,
  title = {{Neural Open Information Extraction}},
  author = {Lei Cui, Furu Wei and Ming Zhou},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-2065},
  url = {https://doi.org/10.18653/v1/p18-2065}
}
```

- [← previous DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension](https://md.research.elamur.ai/free/en/papers/saha-2018-duorc-complex-language-understanding-paraphrased/)
- [next → On the Impact of Various Types of Noise on Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/khayrallah-2018-impact-various-types-noise-neural/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/3/)

## References

31 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. The encoder-decoder framework was introduced by Cho et al. and Sutskever et al., where a multi-layered LSTM/GRU is used to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM/GRU to decode the target sequence from the vector. Bahdanau et al. and Luong et al. furt… [find](https://scholar.google.com/scholar?q=The+encoder%2Ddecoder+framework+was+introduced+by+Cho+et+al%2E+and+Sutskever+et+al%2E%2C+where+a+multi%2Dlayered+LSTM%2FGRU+is+used+to+map+the+input+sequence+to+a+vector+of+a+fixed+dimensionality%2C+and+then+anothe)
2. Gabor Angeli, Melvin Jose Johnson Premkumar, and Christopher D. Manning. 2015. [Leveraging linguistic structure for open domain information extraction](https://md.research.elamur.ai/free/en/papers/angeli-2015-leveraging-linguistic-structure-open-domain/). In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Lang…
3. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. [Neural machine translation by jointly learning to align and translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). CoRR abs/1409.0473. http://arxiv.org/abs/1409.0473. [↗](http://arxiv.org/abs/1409.0473)
4. Michele Banko, Michael J. Cafarella, Stephen Soderland, Matt Broadhead, and Oren Etzioni. 2007. [Open information extraction from the web](https://md.research.elamur.ai/free/en/papers/banko-2007-open-information-extraction-web/). In Proceedings of the 20th International Joint Conference on Artifical Intelligence. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, IJCAI’07, pages 2670…
5. Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Langua… [find](https://scholar.google.com/scholar?q=Kyunghyun+Cho%2C+Bart+van+Merrienboer%2C+Caglar+Gulcehre%2C+Dzmitry+Bahdanau%2C+Fethi+Bougares%2C+Holger+Schwenk%2C+and+Yoshua+Bengio%2E+2014%2E+Learning+phrase+representations+using+rnn+encoder%E2%80%93decoder+for+statistic)
6. Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. 2016. [Pointing the unknown words](https://md.research.elamur.ai/free/en/papers/gulcehre-2016-pointing-unknown-words/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, pages 140–1…
7. Janara Christensen, Mausam, Stephen Soderland, and Oren Etzioni. 2010. Semantic role labeling for open information extraction. In Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading. Association for Computational Linguistics, Los Angel… [find](https://scholar.google.com/scholar?q=Janara+Christensen%2C+Mausam%2C+Stephen+Soderland%2C+and+Oren+Etzioni%2E+2010%2E+Semantic+role+labeling+for+open+information+extraction%2E+In+Proceedings+of+the+NAACL+HLT+2010+First+International+Workshop+on+Form)
8. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput. 9(8):1735– 1780. https://doi.org/10.1162/neco.1997.9.8.1735. [↗](https://doi.org/10.1162/neco.1997.9.8.1735)
9. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M. Rush. 2017. [Opennmt: Open-source toolkit for neural machine translation](https://md.research.elamur.ai/free/en/papers/klein-2017-opennmt-open-source-toolkit-neural/). CoRR abs/1701.02810. http://arxiv.org/abs/1701.02810. [↗](http://arxiv.org/abs/1701.02810)
10. Luciano Del Corro and Rainer Gemulla. 2013. Clausie: Clause-based open information extraction. In Proceedings of the 22Nd International Conference on World Wide Web. ACM, New York, NY, USA, WWW ’13, pages 355–366. https://doi.org/10.1145/2488388.2488420. [↗](https://doi.org/10.1145/2488388.2488420)
11. Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. [Effective approaches to attention-based neural machine translation](https://md.research.elamur.ai/free/en/papers/luong-2015-effective-approaches-attention-based-neural/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, pages 1412– 1421. http…
12. Oren Etzioni, Anthony Fader, Janara Christensen, Stephen Soderland, and Mausam Mausam. 2011. Open information extraction: The second generation. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence - Volume Volume One. AAAI Press, IJCAI’11, pages 3–10. https:… — [doi:10.5591/978-1-57735-516-8/ijcai11-012](https://doi.org/10.5591/978-1-57735-516-8/ijcai11-012) [find](https://scholar.google.com/scholar?q=Oren+Etzioni%2C+Anthony+Fader%2C+Janara+Christensen%2C+Stephen+Soderland%2C+and+Mausam+Mausam%2E+2011%2E+Open+information+extraction%3A+The+second+generation%2E+In+Proceedings+of+the+Twenty%2DSecond+International+Joint)
13. Mausam. 2016. Open information extraction systems and downstream applications. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. AAAI Press, IJCAI’16, pages 4074–4077. [http://dl.acm.org/citation.cfm?id=3061053.3061220](http://dl.acm.org/citation.cfm?id=3061053.3061220). [↗](http://dl.acm.org/citation.cfm?id=3061053.3061220)
14. Anthony Fader, Stephen Soderland, and Oren Etzioni. 2011. Identifying relations for open information extraction. In Proceedings of the Conference of Empirical Methods in Natural Language Processing (EMNLP ’11). Edinburgh, Scotland, UK. [find](https://scholar.google.com/scholar?q=Anthony+Fader%2C+Stephen+Soderland%2C+and+Oren+Etzioni%2E+2011%2E+Identifying+relations+for+open+information+extraction%2E+In+Proceedings+of+the+Conference+of+Empirical+Methods+in+Natural+Language+Processing+%28E)
15. Mausam, Michael Schmitz, Robert Bart, Stephen Soderland, and Oren Etzioni. 2012. Open language learning for information extraction. In Proceedings of Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CONLL). [find](https://scholar.google.com/scholar?q=Mausam%2C+Michael+Schmitz%2C+Robert+Bart%2C+Stephen+Soderland%2C+and+Oren+Etzioni%2E+2012%2E+Open+language+learning+for+information+extraction%2E+In+Proceedings+of+Conference+on+Empirical+Methods+in+Natural+Languag)
16. Kiril Gashteovski, Rainer Gemulla, and Luciano Del Corro. 2017. Minie: Minimizing facts in open information extraction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, pages 2630– 2640. https:/… [find](https://scholar.google.com/scholar?q=Kiril+Gashteovski%2C+Rainer+Gemulla%2C+and+Luciano+Del+Corro%2E+2017%2E+Minie%3A+Minimizing+facts+in+open+information+extraction%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Language+P)
17. Rui Meng, Sanqiang Zhao, Shuguang Han, Daqing He, Peter Brusilovsky, and Yu Chi. 2017. [Deep keyphrase generation](https://md.research.elamur.ai/free/en/papers/meng-2017-deep-keyphrase-generation/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada, pages 58…
18. Jonas Gehring, Michael Auli, David Grangier, and Yann N Dauphin. 2016. [A Convolutional Encoder Model for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/gehring-2017-convolutional-encoder-model-neural-machine/). ArXiv eprints .
19. Ramesh Nallapati, Bowen Zhou, Cı́cero Nogueira dos Santos, aglar Gülehre, and Bing Xiang. 2016. Abstractive text summarization using sequence-to-sequence rnns and beyond. In CoNLL. [find](https://scholar.google.com/scholar?q=Ramesh+Nallapati%2C+Bowen+Zhou%2C+C%C4%B1%CC%81cero+Nogueira+dos+Santos%2C+aglar+Gu%CC%88lehre%2C+and+Bing+Xiang%2E+2016%2E+Abstractive+text+summarization+using+sequence%2Dto%2Dsequence+rnns+and+beyond%2E+In+CoNLL%2E)
20. Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, and Yann N Dauphin. 2017. [Convolutional Sequence to Sequence Learning](https://md.research.elamur.ai/free/en/papers/gehring-2017-convolutional-sequence-sequence-learning/). ArXiv e-prints .
21. Harinder Pal and Mausam. 2016. Demonyms and compound relational nouns in nominal open ie. In Proceedings of the 5th Workshop on Automated Knowledge Base Construction. Association for Computational Linguistics, San Diego, CA, pages 35–39. [http://www.aclweb.org/anthology/W16-1307](http://www.aclweb.org/anthology/W16-1307). [↗](http://www.aclweb.org/anthology/W16-1307)
22. Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O.K. Li. 2016. [Incorporating copying mechanism in sequence-to-sequence learning](https://md.research.elamur.ai/free/en/papers/gu-2016-incorporating-copying-mechanism-sequence-sequence/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolf…
23. Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, pages 379–389. http://aclw… [find](https://scholar.google.com/scholar?q=Alexander+M%2E+Rush%2C+Sumit+Chopra%2C+and+Jason+Weston%2E+2015%2E+A+neural+attention+model+for+abstractive+sentence+summarization%2E+In+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natural+Language)
24. Swarnadeep Saha, Harinder Pal, and Mausam. 2017. Bootstrapping for numerical open ie. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Vancouver, Canada, pages 317–323. [http://aclweb.org/an…](http://aclweb.org/an…) [↗](http://aclweb.org/an…)
25. Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, and Alexander Löser. 2017. Analysing errors of open information extraction systems. In Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems. Association for Computational Linguistics, Copenhagen, Denmar… [find](https://scholar.google.com/scholar?q=Rudolf+Schneider%2C+Tom+Oberhauser%2C+Tobias+Klatt%2C+Felix+A%2E+Gers%2C+and+Alexander+Lo%CC%88ser%2E+2017%2E+Analysing+errors+of+open+information+extraction+systems%2E+In+Proceedings+of+the+First+Workshop+on+Building+Lin)
26. Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. 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). Association for Computational Linguistics, Vancouver, Cana… [find](https://scholar.google.com/scholar?q=Abigail+See%2C+Peter+J%2E+Liu%2C+and+Christopher+D%2E+Manning%2E+2017%2E+Get+to+the+point%3A+Summarization+with+pointer%2Dgenerator+networks%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computati)
27. Gabriel Stanovsky and Ido Dagan. 2016. Creating a large benchmark for open information extraction. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, pages 2300–2305. [https://aclweb.org/anthology/D16-12…](https://aclweb.org/anthology/D16-12…) [↗](https://aclweb.org/anthology/D16-12…)
28. Gabriel Stanovsky, Jessica Ficler, Ido Dagan, and Yoav Goldberg. 2016. Getting more out of syntax with props. CoRR abs/1603.01648. http://arxiv.org/abs/1603.01648. — [arXiv:1603.01648](https://arxiv.org/abs/1603.01648) [↗](http://arxiv.org/abs/1603.01648)
29. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. CoRR abs/1409.3215. http://arxiv.org/abs/1409.3215. [↗](http://arxiv.org/abs/1409.3215)
30. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Proces…
31. Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2014. [Show and tell: A neural image caption generator](https://md.research.elamur.ai/free/en/papers/vinyals-2014-show-tell-neural-image-caption/). CoRR abs/1411.4555. http://arxiv.org/abs/1411.4555. [↗](http://arxiv.org/abs/1411.4555)

*Updated 24 October 2026*