---
title: "Representing Text for Joint Embedding of — Toutanova 2015"
description: "Knowledge bases such as Freebase are large but still miss many facts."
authors: ["Kristina Toutanova", "Danqi Chen", "Patrick Pantel", "Hoifung Poon", "Pallavi Choudhury", "Michael Gamon"]
year: 2015
venue: "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D15-1174/"
doi: "10.18653/v1/d15-1174"
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/toutanova-2015-representing-text-joint-embedding-text/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/toutanova-2015-representing-text-joint-embedding-text/)

[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/page/2/) / Representing Text for Joint Embedding of Text and Knowledge Bases

# Representing Text for Joint Embedding of Text and Knowledge Bases

**Authors:** [Kristina Toutanova](https://md.research.elamur.ai/free/en/authors/kristina-toutanova/), [Danqi Chen](https://md.research.elamur.ai/free/en/authors/danqi-chen/), [Patrick Pantel](https://md.research.elamur.ai/free/en/authors/patrick-pantel/), [Hoifung Poon](https://md.research.elamur.ai/free/en/authors/hoifung-poon/), Pallavi Choudhury, [Michael Gamon](https://md.research.elamur.ai/free/en/authors/michael-gamon/) · **Year:** 2015 · **Venue:** Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · **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/D15-1174/) · [PDF](https://aclanthology.org/D15-1174.pdf) · [DOI 10.18653/v1/d15-1174](https://doi.org/10.18653/v1/d15-1174) · [OpenAlex](https://openalex.org/W2250635077)

**Citations:** 750 citations (openalex-snapshot · 2026-10-14) · [154](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Knowledge bases such as Freebase are large but still miss many facts. Earlier "universal schema" work (Riedel et al., 2013) put KB relations and textual relations into one shared vector space, so that each source can inform predictions from the other. In that setup, every lexicalized dependency path between two entities was an atomic relation with its own vector. This ignores the fact that many near-synonymous paths share words and dependency arcs.

The authors instead build each textual relation's vector from its parts. A one-hidden-layer convolutional network runs over the words and arcs of the path. This network is trained jointly with entity and KB relation embeddings, under a single link-prediction loss in which the text term gets its own weight.

They evaluate on FB15k-237, paired with ClueWeb12 sentences that carry Freebase entity annotations. Compositional text representations clearly beat atomic ones, and the gains are largest for entity pairs that have textual mentions. This shows that sharing parameters across textual patterns makes text far more useful for KB completion.

## Key points
- **Base models.** The work extends three prior scoring models: E, F (entity-pair vectors) and DistMult. Each gets a CONV variant in which textual relation vectors come from a CNN over dependency paths.
- **Data.** FB15k-237 is a version of FB15k with highly redundant relations filtered out. Text comes from ClueWeb12 with FACC1 Freebase entity annotations.
- **Main result.** The best system, CONV-E+CONV-DistMult, raises MRR by 2.4 points overall and by 5 points on test triples with textual mentions, compared with the atomic-text version. Model F gains 2.5 MRR from text but stays weak overall. Model E gets no benefit from text, and its optimal text weight is zero.
- **Best configuration.** Text-loss weight τ = 0.25, L2 weight λ = 1, convolution window 3, and pre-trained Turian et al. word vectors. This reaches 40.4 validation MRR.
- **Sensitivity results.**
  - Setting τ = 1 drops MRR to 39.6.
  - Setting λ = 25 drops it to 38.9.
  - Random word initialization gives 40.3.
  - Initializing from a KB-only model gives 38.7.
  - A window of 5 gives 40.6.
  - Full entity-pair vectors would have required about 2.2 billion parameters.

## Interesting ideas
- **Compose sparse symbolic patterns instead of memorizing them.** Building a dependency path's vector from its words and arcs lets rare patterns borrow strength from frequent, similar ones. The same trick could help with sparse templates, query patterns or lexico-syntactic rules elsewhere.
- **Down-weight the noisy auxiliary signal.** Adding text as a separately weighted term in one joint loss worked better than weighting text and KB equally. This is a simple, tunable recipe for multi-source training when one source is noisier.
- **Use a context-free prior to temper noisy evidence.** Model E scores arguments without looking at the other entity, yet pairing it with DistMult gave the biggest gains. The authors suggest the prior blocks implausible answers that noisy textual patterns would otherwise push up. Combining a cheap type-like model with a richer one may help in many ranking tasks.
- **Evaluate automatically under a local closed-world assumption.** Ranking candidate fillers for (subject, relation, ?) queries avoids human labeling of extractions. The assumption is mild, especially for nearly functional relations, which makes this a practical protocol for evaluating relation extraction on any KB.
- **Break down results by text coverage.** Reporting scores separately for test triples with and without textual mentions shows exactly where the text signal helps. This kind of slicing is worth copying whenever an auxiliary resource covers only part of the data.

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

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

154 papers of our library cite it (of the 140884 whose bibliographies we read); 5 of them have a page here, 149 not yet.

- [Rewarding Coreference Resolvers for Being Consistent with World Knowledge](https://md.research.elamur.ai/free/en/papers/aralikatte-2019-rewarding-coreference-resolvers-being-consistent/)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://md.research.elamur.ai/free/en/papers/balazevic-2019-tucker-tensor-factorization-knowledge-graph/)
- [How Can We Know What Language Models Know?](https://md.research.elamur.ai/free/en/papers/jiang-2020-how-can-we-know-what/)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://md.research.elamur.ai/free/en/papers/liu-2019-k-bert-enabling-language-representation/)
- [Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://md.research.elamur.ai/free/en/papers/strubell-2017-fast-accurate-entity-recognition-iterated/)

## Cite

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

```bibtex
@inproceedings{toutanova2015representing,
  title = {{Representing Text for Joint Embedding of Text and Knowledge Bases}},
  author = {Toutanova, Kristina and Chen, Danqi and Pantel, Patrick and Poon, Hoifung and Choudhury, Pallavi and Gamon, Michael},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1174},
  url = {https://doi.org/10.18653/v1/d15-1174}
}
```

- [← previous Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval](https://md.research.elamur.ai/free/en/papers/liu-2015-representation-learning-multi-task-deep/)
- [next → Rule-based Coreference Resolution in German Historic Novels](https://md.research.elamur.ai/free/en/papers/krug-2015-rule-based-coreference-resolution-german/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/page/2/)

## References

32 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. 2007. Dbpedia: A nucleus for a web of open data. Springer. [find](https://scholar.google.com/scholar?q=So%CC%88ren+Auer%2C+Christian+Bizer%2C+Georgi+Kobilarov%2C+Jens+Lehmann%2C+Richard+Cyganiak%2C+and+Zachary+Ives%2E+2007%2E+Dbpedia%3A+A+nucleus+for+a+web+of+open+data%2E+Springer%2E)
2. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250. ACM. [find](https://scholar.google.com/scholar?q=Kurt+Bollacker%2C+Colin+Evans%2C+Praveen+Paritosh%2C+Tim+Sturge%2C+and+Jamie+Taylor%2E+2008%2E+Freebase%3A+a+collaboratively+created+graph+database+for+structuring+human+knowledge%2E+In+Proceedings+of+the+2008+ACM+SI)
3. Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems (NIPS). [find](https://scholar.google.com/scholar?q=Antoine+Bordes%2C+Nicolas+Usunier%2C+Alberto+Garcia%2DDuran%2C+Jason+Weston%2C+and+Oksana+Yakhnenko%2E+2013%2E+Translating+embeddings+for+modeling+multi%2Drelational+data%2E+In+Advances+in+Neural+Information+Processing)
4. Kai-Wei Chang, Wen-tau Yih, Bishan Yang, and Christopher Meek. 2014. Typed tensor decomposition of knowledge bases for relation extraction. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=Kai%2DWei+Chang%2C+Wen%2Dtau+Yih%2C+Bishan+Yang%2C+and+Christopher+Meek%2E+2014%2E+Typed+tensor+decomposition+of+knowledge+bases+for+relation+extraction%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E)
5. Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, and Wei Zhang. 2014. Knowledge vault: A web-scale approach to probabilistic knowledge fusion. In International Conference on Knowledge Discovery and Data Mining (KDD). [find](https://scholar.google.com/scholar?q=Xin+Dong%2C+Evgeniy+Gabrilovich%2C+Geremy+Heitz%2C+Wilko+Horn%2C+Ni+Lao%2C+Kevin+Murphy%2C+Thomas+Strohmann%2C+Shaohua+Sun%2C+and+Wei+Zhang%2E+2014%2E+Knowledge+vault%3A+A+web%2Dscale+approach+to+probabilistic+knowledge+fusi)
6. Evgeniy Gabrilovich, Michael Ringgaard, and Amarnag Subramanya. 2013. FACC1: Freebase annotation of ClueWeb corpora, Version 1 (release date 2013-06-26, format version 1, correction level 0). [find](https://scholar.google.com/scholar?q=Evgeniy+Gabrilovich%2C+Michael+Ringgaard%2C+and+Amarnag+Subramanya%2E+2013%2E+FACC1%3A+Freebase+annotation+of+ClueWeb+corpora%2C+Version+1+%28release+date+2013%2D06%2D26%2C+format+version+1%2C+correction+level+0%29%2E)
7. Matt Gardner, Partha Pratim Talukdar, Bryan Kisiel, and Tom Mitchell. 2013. Improving learning and inference in a large knowledge-base using latent syntactic cues. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=Matt+Gardner%2C+Partha+Pratim+Talukdar%2C+Bryan+Kisiel%2C+and+Tom+Mitchell%2E+2013%2E+Improving+learning+and+inference+in+a+large+knowledge%2Dbase+using+latent+syntactic+cues%2E+In+Empirical+Methods+in+Natural+Lang)
8. Matt Gardner, Partha Talukdar, Jayant Krishnamurthy, and Tom Mitchell. 2014. Incorporating vector space similarity in random walk inference over knowledge bases. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=Matt+Gardner%2C+Partha+Talukdar%2C+Jayant+Krishnamurthy%2C+and+Tom+Mitchell%2E+2014%2E+Incorporating+vector+space+similarity+in+random+walk+inference+over+knowledge+bases%2E+In+Empirical+Methods+in+Natural+Langua)
9. Matthew R Gormley, Mo Yu, and Mark Dredze. 2015. Improved relation extraction with feature-rich compositional embedding models. arXiv preprint arXiv:1505.02419. [find](https://scholar.google.com/scholar?q=Matthew+R+Gormley%2C+Mo+Yu%2C+and+Mark+Dredze%2E+2015%2E+Improved+relation+extraction+with+feature%2Drich+compositional+embedding+models%2E+arXiv+preprint+arXiv%3A1505%2E02419%2E)
10. Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke Zettlemoyer, and Daniel S. Weld. 2011. Knowledge-based weak supervision for information extraction of overlapping relations. In Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Raphael+Hoffmann%2C+Congle+Zhang%2C+Xiao+Ling%2C+Luke+Zettlemoyer%2C+and+Daniel+S%2E+Weld%2E+2011%2E+Knowledge%2Dbased+weak+supervision+for+information+extraction+of+overlapping+relations%2E+In+Association+for+Computat)
11. Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882. [find](https://scholar.google.com/scholar?q=Yoon+Kim%2E+2014%2E+Convolutional+neural+networks+for+sentence+classification%2E+arXiv+preprint+arXiv%3A1408%2E5882%2E) [our card](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/)
12. Ni Lao, Tom Mitchell, and William W Cohen. 2011. Random walk inference and learning in a large scale knowledge base. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=Ni+Lao%2C+Tom+Mitchell%2C+and+William+W+Cohen%2E+2011%2E+Random+walk+inference+and+learning+in+a+large+scale+knowledge+base%2E+In+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2E)
13. Ni Lao, Amarnag Subramanya, Fernando Pereira, and William W Cohen. 2012. Reading the web with learned syntactic-semantic inference rules. In Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL). [find](https://scholar.google.com/scholar?q=Ni+Lao%2C+Amarnag+Subramanya%2C+Fernando+Pereira%2C+and+William+W+Cohen%2E+2012%2E+Reading+the+web+with+learned+syntactic%2Dsemantic+inference+rules%2E+In+Empirical+Methods+in+Natural+Language+Processing+and+Comput)
14. Dong C Liu and Jorge Nocedal. 1989. On the limited memory bfgs method for large scale optimization. Mathematical programming, 45(1-3):503–528. [find](https://scholar.google.com/scholar?q=Dong+C+Liu+and+Jorge+Nocedal%2E+1989%2E+On+the+limited+memory+bfgs+method+for+large+scale+optimization%2E+Mathematical+programming%2C+45%281%2D3%29%3A503%E2%80%93528%2E)
15. Mike Mintz, Steven Bills, Rion Snow, and Daniel Jurafsky. 2009. Distant supervision for relation extraction without labeled data. In Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP). [find](https://scholar.google.com/scholar?q=Mike+Mintz%2C+Steven+Bills%2C+Rion+Snow%2C+and+Daniel+Jurafsky%2E+2009%2E+Distant+supervision+for+relation+extraction+without+labeled+data%2E+In+Association+for+Computational+Linguistics+and+International+Joint+C)
16. Arvind Neelakantan, Benjamin Roth, and Andrew Mc-Callum. 2015. Compositional vector space models for knowledge base completion. In ACL. [find](https://scholar.google.com/scholar?q=Arvind+Neelakantan%2C+Benjamin+Roth%2C+and+Andrew+Mc%2DCallum%2E+2015%2E+Compositional+vector+space+models+for+knowledge+base+completion%2E+In+ACL%2E)
17. Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A three-way model for collective learning on multi-relational data. In Proceedings of the 28th international conference on machine learning (ICML-11), pages 809–816. [find](https://scholar.google.com/scholar?q=Maximilian+Nickel%2C+Volker+Tresp%2C+and+Hans%2DPeter+Kriegel%2E+2011%2E+A+three%2Dway+model+for+collective+learning+on+multi%2Drelational+data%2E+In+Proceedings+of+the+28th+international+conference+on+machine+learni)
18. Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2015. A review of relational machine learning for knowledge graphs: From multi-relational link prediction to automated knowledge graph construction. arXiv preprint arXiv:1503.00759. [find](https://scholar.google.com/scholar?q=Maximilian+Nickel%2C+Kevin+Murphy%2C+Volker+Tresp%2C+and+Evgeniy+Gabrilovich%2E+2015%2E+A+review+of+relational+machine+learning+for+knowledge+graphs%3A+From+multi%2Drelational+link+prediction+to+automated+knowledge)
19. Sebastian Riedel, Limin Yao, and Andrew McCallum. 2010. Modeling relations and their mentions without labeled text. In Machine Learning and Knowledge Discovery in Databases, pages 148–163. Springer. [find](https://scholar.google.com/scholar?q=Sebastian+Riedel%2C+Limin+Yao%2C+and+Andrew+McCallum%2E+2010%2E+Modeling+relations+and+their+mentions+without+labeled+text%2E+In+Machine+Learning+and+Knowledge+Discovery+in+Databases%2C+pages+148%E2%80%93163%2E+Springer%2E)
20. Sebastian Riedel, Limin Yao, Benjamin M. Marlin, and Andrew McCallum. 2013. Relation extraction with matrix factorization and universal schemas. In North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). [find](https://scholar.google.com/scholar?q=Sebastian+Riedel%2C+Limin+Yao%2C+Benjamin+M%2E+Marlin%2C+and+Andrew+McCallum%2E+2013%2E+Relation+extraction+with+matrix+factorization+and+universal+schemas%2E+In+North+American+Chapter+of+the+Association+for+Comput)
21. Martin Riedmiller and Heinrich Braun. 1993. A direct adaptive method for faster backpropagation learning: The rprop algorithm. In Neural Networks, 1993., IEEE International Conference on, pages 586–591. IEEE. [find](https://scholar.google.com/scholar?q=Martin+Riedmiller+and+Heinrich+Braun%2E+1993%2E+A+direct+adaptive+method+for+faster+backpropagation+learning%3A+The+rprop+algorithm%2E+In+Neural+Networks%2C+1993%2E%2C+IEEE+International+Conference+on%2C+pages+586%E2%80%9359)
22. Alan Ritter, Luke Zettlemoyer, Oren Etzioni, et al. 2013. Modeling missing data in distant supervision for information extraction. Transactions of the Association for Computational Linguistics, 1:367–378. [find](https://scholar.google.com/scholar?q=Alan+Ritter%2C+Luke+Zettlemoyer%2C+Oren+Etzioni%2C+et+al%2E+2013%2E+Modeling+missing+data+in+distant+supervision+for+information+extraction%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+1%3A367%E2%80%93)
23. Fabian M Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: a core of semantic knowledge. In Proceedings of the 16th international conference on World Wide Web, pages 697–706. ACM. [find](https://scholar.google.com/scholar?q=Fabian+M+Suchanek%2C+Gjergji+Kasneci%2C+and+Gerhard+Weikum%2E+2007%2E+Yago%3A+a+core+of+semantic+knowledge%2E+In+Proceedings+of+the+16th+international+conference+on+World+Wide+Web%2C+pages+697%E2%80%93706%2E+ACM%2E)
24. Mihai Surdeanu, Julie Tibshirani, Ramesh Nallapati, and Christopher D. Manning. 2012. Multi-instance multi-label learning for relation extraction. In Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNLL). [find](https://scholar.google.com/scholar?q=Mihai+Surdeanu%2C+Julie+Tibshirani%2C+Ramesh+Nallapati%2C+and+Christopher+D%2E+Manning%2E+2012%2E+Multi%2Dinstance+multi%2Dlabel+learning+for+relation+extraction%2E+In+Empirical+Methods+in+Natural+Language+Processing+a)
25. Kai Sheng Tai, Richard Socher, and Christopher D Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075. [find](https://scholar.google.com/scholar?q=Kai+Sheng+Tai%2C+Richard+Socher%2C+and+Christopher+D+Manning%2E+2015%2E+Improved+semantic+representations+from+tree%2Dstructured+long+short%2Dterm+memory+networks%2E+arXiv+preprint+arXiv%3A1503%2E00075%2E)
26. Kristina Toutanova and Danqi Chen. 2015. Observed versus latent features for knowledge base and text inference. In Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pages 57–66. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kristina+Toutanova+and+Danqi+Chen%2E+2015%2E+Observed+versus+latent+features+for+knowledge+base+and+text+inference%2E+In+Proceedings+of+the+3rd+Workshop+on+Continuous+Vector+Space+Models+and+their+Compositi)
27. Joseph Turian, Lev Ratinov, and Yoshua Bengio. 2010. Word representations: a simple and general method for semi-supervised learning. In Proceedings of the 48th annual meeting of the association for computational linguistics, pages 384–394. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Joseph+Turian%2C+Lev+Ratinov%2C+and+Yoshua+Bengio%2E+2010%2E+Word+representations%3A+a+simple+and+general+method+for+semi%2Dsupervised+learning%2E+In+Proceedings+of+the+48th+annual+meeting+of+the+association+for+co) [our card](https://md.research.elamur.ai/free/en/papers/turian-2010-word-representations-simple-general-method/)
28. Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014a. Knowledge graph and text jointly embedding. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, pages 1591–1601. [find](https://scholar.google.com/scholar?q=Zhen+Wang%2C+Jianwen+Zhang%2C+Jianlin+Feng%2C+and+Zheng+Chen%2E+2014a%2E+Knowledge+graph+and+text+jointly+embedding%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EM)
29. Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014b. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, pages 1112–1119. [find](https://scholar.google.com/scholar?q=Zhen+Wang%2C+Jianwen+Zhang%2C+Jianlin+Feng%2C+and+Zheng+Chen%2E+2014b%2E+Knowledge+graph+embedding+by+translating+on+hyperplanes%2E+In+Proceedings+of+the+Twenty%2DEighth+AAAI+Conference+on+Artificial+Intelligence%2C+)
30. Jason Weston, Antoine Bordes, Oksana Yakhnenko, and Nicolas Usunier. 2013. Connecting language and knowledge bases with embedding models for relation extraction. In Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=Jason+Weston%2C+Antoine+Bordes%2C+Oksana+Yakhnenko%2C+and+Nicolas+Usunier%2E+2013%2E+Connecting+language+and+knowledge+bases+with+embedding+models+for+relation+extraction%2E+In+Empirical+Methods+in+Natural+Langua)
31. Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Bishan+Yang%2C+Wen%2Dtau+Yih%2C+Xiaodong+He%2C+Jianfeng+Gao%2C+and+Li+Deng%2E+2015%2E+Embedding+entities+and+relations+for+learning+and+inference+in+knowledge+bases%2E+In+International+Conference+on+Learning+Represen)
32. Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. 2014. Relation classification via convolutional deep neural network. In Proceedings of COLING, pages 2335–2344. [find](https://scholar.google.com/scholar?q=Daojian+Zeng%2C+Kang+Liu%2C+Siwei+Lai%2C+Guangyou+Zhou%2C+and+Jun+Zhao%2E+2014%2E+Relation+classification+via+convolutional+deep+neural+network%2E+In+Proceedings+of+COLING%2C+pages+2335%E2%80%932344%2E) [our card](https://md.research.elamur.ai/free/en/papers/zeng-2014-relation-classification-convolutional-deep-neural/)