---
title: "Multilingual Models for Compositional — Hermann 2014"
description: "Most compositional semantic models depend on parse trees, word alignments, or task labels such as sentiment, which limits them to well-resourced languages."
authors: ["Karl Moritz Hermann", "Phil Blunsom"]
year: 2014
venue: "Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P14-1006/"
doi: "10.3115/v1/p14-1006"
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/hermann-2014-multilingual-models-compositional-distributed-semantics/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hermann-2014-multilingual-models-compositional-distributed-semantics/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2014](https://md.research.elamur.ai/free/en/papers/2014/page/2/) / Multilingual Models for Compositional Distributed Semantics

# Multilingual Models for Compositional Distributed Semantics

**Authors:** [Karl Moritz Hermann](https://md.research.elamur.ai/free/en/authors/karl-moritz-hermann/), [Phil Blunsom](https://md.research.elamur.ai/free/en/authors/phil-blunsom/) · **Year:** 2014 · **Venue:** Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **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/P14-1006/) · [PDF](https://aclanthology.org/P14-1006.pdf) · [DOI 10.3115/v1/p14-1006](https://doi.org/10.3115/v1/p14-1006) · [OpenAlex](https://openalex.org/W2142074148)

**Citations:** 268 citations (openalex-snapshot · 2026-10-14) · [107](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Most compositional semantic models depend on parse trees, word alignments, or task labels such as sentiment, which limits them to well-resourced languages. Hermann and Blunsom remove these requirements. They learn word embeddings and composed sentence and document vectors using only sentence-aligned parallel text. Each language gets its own compositional vector model (CVM). Training pulls the vectors of translation pairs together and uses a noise-contrastive hinge loss to push randomly sampled non-translations at least a margin apart. The authors test two syntax-free composition functions: ADD, a summed bag of words, and BI, which applies tanh over adjacent word pairs. They also stack a second CVM over sentence vectors to produce document representations. The models are trained on Europarl v7 and on a new multilingual corpus built from TED talks. On cross-lingual document classification with Reuters RCV1/RCV2, they outperform the best previously reported results, those of Klementiev et al. (2012). Qualitative analysis shows they also align languages that never appeared together in training. The method suits low-resource settings where only bitext is available.

## Key points
- The training signal is the squared Euclidean distance between the two sentence encodings, wrapped in a margin-based hinge loss over sampled negative sentences, plus L2 regularisation. No word alignment or syntax is used.
- The four variants are ADD, BI, DOC/ADD and DOC/BI. The DOC versions add a document-level composition and error signal on top of the sentence-level one.
- Europarl v7 (English-German and English-French, with the last 100,000 sentences of each pair held out for development) supplied the embeddings for the RCV1/RCV2 classification task.
- The new TED-based corpus is derived from IWSLT 2013:
  - it has 12,078 parallel documents across 12 language pairs and about 1.68M non-English sentences;
  - talks with id ≥ 1,400 (roughly 10%) form the test set;
  - the 15 most frequent talk keywords serve as multi-label topic classes.
- In t-SNE plots from the BI+ model trained on Europarl, French and German words and phrases cluster by meaning, even though no French-German parallel data was used. English acted as a pivot.

## Interesting ideas
- **Translation as free supervision.** Treating a translation pair as two views of the same meaning gives a training signal without annotation. This could help build Ukrainian sentence embeddings from existing Ukrainian-English bitext alone.
- **Contrastive margin against collapse.** Minimising the distance between positives alone would let all vectors shrink to one point. Adding sampled negatives with a hinge margin prevents this cheaply, and the trick transfers to any paired-embedding setup.
- **Hierarchical composition for documents.** Composing sentence vectors through a second CVM, instead of averaging them, lets document-aligned but sentence-unaligned corpora still train the word vectors. This is useful when only loosely aligned parallel documents exist.
- **Repurposing metadata as a benchmark.** Using TED talk keywords as topic labels turned a machine-translation corpus into a many-language classification benchmark. Other parallel collections with tags could be converted the same way for evaluation.
- **Checking pivot effects.** Inspecting language pairs that never co-occurred in training (here French-German, linked through English) is a simple test of whether the space is truly shared. This matters when Ukrainian is connected to other languages mainly through English.

*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

107 papers of our library cite it (of the 140884 whose bibliographies we read); 4 of them have a page here, 103 not yet.

- [Cross-lingual Dependency Parsing Based on Distributed Representations](https://md.research.elamur.ai/free/en/papers/guo-2015-cross-lingual-dependency-parsing-based/)
- [GLUECoS: An Evaluation Benchmark for Code-Switched NLP](https://md.research.elamur.ai/free/en/papers/khanuja-2020-gluecos-evaluation-benchmark-code-switched/)
- [URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors](https://md.research.elamur.ai/free/en/papers/littell-2017-uriel-lang2vec-representing-languages-as/)
- [Learning Joint Multilingual Sentence Representations with Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/schwenk-2017-learning-joint-multilingual-sentence-representations/)

## Cite

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

```bibtex
@inproceedings{hermann2014multilingual,
  title = {{Multilingual Models for Compositional Distributed Semantics}},
  author = {Hermann, Karl Moritz and Blunsom, Phil},
  booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2014},
  doi = {10.3115/v1/p14-1006},
  url = {https://doi.org/10.3115/v1/p14-1006}
}
```

- [← previous MUHIT: A Multilingual Harmonized Dictionary](https://md.research.elamur.ai/free/en/papers/alansary-2014-muhit-multilingual-harmonized-dictionary/)
- [next → N-gram Counts and Language Models from the Common Crawl](https://md.research.elamur.ai/free/en/papers/buck-2014-n-gram-counts-language-models/)
- [↑ back to papers of 2014](https://md.research.elamur.ai/free/en/papers/2014/page/2/)

## References

41 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. R. Al-Rfou’, B. Perozzi, and S. Skiena. 2013. Polyglot: Distributed word representations for multilingual nlp. In Proceedings of CoNLL. [find](https://scholar.google.com/scholar?q=R%2E+Al%2DRfou%E2%80%99%2C+B%2E+Perozzi%2C+and+S%2E+Skiena%2E+2013%2E+Polyglot%3A+Distributed+word+representations+for+multilingual+nlp%2E+In+Proceedings+of+CoNLL%2E) [our card](https://md.research.elamur.ai/free/en/papers/rfou-2013-polyglot-distributed-word-representations-multilingual/)
2. M. Baroni and R. Zamparelli. 2010. Nouns are vectors, adjectives are matrices: Representing adjective-noun constructions in semantic space. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=M%2E+Baroni+and+R%2E+Zamparelli%2E+2010%2E+Nouns+are+vectors%2C+adjectives+are+matrices%3A+Representing+adjective%2Dnoun+constructions+in+semantic+space%2E+In+Proceedings+of+EMNLP%2E)
3. Y. Bengio, R. Ducharme, P. Vincent, and C. Janvin. 2003. A neural probabilistic language model. Journal of Machine Learning Research, 3:1137–1155, March. [find](https://scholar.google.com/scholar?q=Y%2E+Bengio%2C+R%2E+Ducharme%2C+P%2E+Vincent%2C+and+C%2E+Janvin%2E+2003%2E+A+neural+probabilistic+language+model%2E+Journal+of+Machine+Learning+Research%2C+3%3A1137%E2%80%931155%2C+March%2E)
4. D. M. Blei, A. Y. Ng, and M. I. Jordan. 2003. Latent dirichlet allocation. Journal of Machine Learning Research, 3:993–1022. [find](https://scholar.google.com/scholar?q=D%2E+M%2E+Blei%2C+A%2E+Y%2E+Ng%2C+and+M%2E+I%2E+Jordan%2E+2003%2E+Latent+dirichlet+allocation%2E+Journal+of+Machine+Learning+Research%2C+3%3A993%E2%80%931022%2E) [our card](https://md.research.elamur.ai/free/en/papers/blei-2003-latent-dirichlet-allocation/)
5. P. Bloom. 2001. Precis of how children learn the meanings of words. Behavioral and Brain Sciences, 24:1095–1103. [find](https://scholar.google.com/scholar?q=P%2E+Bloom%2E+2001%2E+Precis+of+how+children+learn+the+meanings+of+words%2E+Behavioral+and+Brain+Sciences%2C+24%3A1095%E2%80%931103%2E)
6. M. Cettolo, C. Girardi, and M. Federico. 2012. Wit 3 : Web inventory of transcribed and translated talks. In Proceedings of EAMT. [find](https://scholar.google.com/scholar?q=M%2E+Cettolo%2C+C%2E+Girardi%2C+and+M%2E+Federico%2E+2012%2E+Wit+3+%3A+Web+inventory+of+transcribed+and+translated+talks%2E+In+Proceedings+of+EAMT%2E)
7. S. Clark and S. Pulman. 2007. Combining symbolic and distributional models of meaning. In Proceedings of AAAI Spring Symposium on Quantum Interaction. AAAI Press. [find](https://scholar.google.com/scholar?q=S%2E+Clark+and+S%2E+Pulman%2E+2007%2E+Combining+symbolic+and+distributional+models+of+meaning%2E+In+Proceedings+of+AAAI+Spring+Symposium+on+Quantum+Interaction%2E+AAAI+Press%2E)
8. T. Cohn and M. Lapata. 2007. Machine translation by triangulation: Making effective use of multi-parallel corpora. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=T%2E+Cohn+and+M%2E+Lapata%2E+2007%2E+Machine+translation+by+triangulation%3A+Making+effective+use+of+multi%2Dparallel+corpora%2E+In+Proceedings+of+ACL%2E)
9. M. Collins. 2002. Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In Proceedings of ACL-EMNLP. [find](https://scholar.google.com/scholar?q=M%2E+Collins%2E+2002%2E+Discriminative+training+methods+for+hidden+markov+models%3A+Theory+and+experiments+with+perceptron+algorithms%2E+In+Proceedings+of+ACL%2DEMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/collins-2002-discriminative-training-methods-hidden-markov/)
10. R. Collobert and J. Weston. 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of ICML. [find](https://scholar.google.com/scholar?q=R%2E+Collobert+and+J%2E+Weston%2E+2008%2E+A+unified+architecture+for+natural+language+processing%3A+Deep+neural+networks+with+multitask+learning%2E+In+Proceedings+of+ICML%2E)
11. R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa. 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12:2493–2537. [find](https://scholar.google.com/scholar?q=R%2E+Collobert%2C+J%2E+Weston%2C+L%2E+Bottou%2C+M%2E+Karlen%2C+K%2E+Kavukcuoglu%2C+and+P%2E+Kuksa%2E+2011%2E+Natural+language+processing+%28almost%29+from+scratch%2E+Journal+of+Machine+Learning+Research%2C+12%3A2493%E2%80%932537%2E) [our card](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/)
12. J. Duchi, E. Hazan, and Y. Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12:2121–2159, July. [find](https://scholar.google.com/scholar?q=J%2E+Duchi%2C+E%2E+Hazan%2C+and+Y%2E+Singer%2E+2011%2E+Adaptive+subgradient+methods+for+online+learning+and+stochastic+optimization%2E+Journal+of+Machine+Learning+Research%2C+12%3A2121%E2%80%932159%2C+July%2E)
13. S. T. Dumais, G. W. Furnas, T. K. Landauer, S. Deerwester, and R. Harshman. 1988. Using latent semantic analysis to improve access to textual information. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. [find](https://scholar.google.com/scholar?q=S%2E+T%2E+Dumais%2C+G%2E+W%2E+Furnas%2C+T%2E+K%2E+Landauer%2C+S%2E+Deerwester%2C+and+R%2E+Harshman%2E+1988%2E+Using+latent+semantic+analysis+to+improve+access+to+textual+information%2E+In+Proceedings+of+the+SIGCHI+Conference+on+Hu)
14. C. Dyer, A. Lopez, J. Ganitkevitch, J. Weese, F. Ture, P. Blunsom, H. Setiawan, V. Eidelman, and P. Resnik. 2010. cdec: A Decoder, Alignment, and Learning framework for finite-state and context-free translation models. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=C%2E+Dyer%2C+A%2E+Lopez%2C+J%2E+Ganitkevitch%2C+J%2E+Weese%2C+F%2E+Ture%2C+P%2E+Blunsom%2C+H%2E+Setiawan%2C+V%2E+Eidelman%2C+and+P%2E+Resnik%2E+2010%2E+cdec%3A+A+Decoder%2C+Alignment%2C+and+Learning+framework+for+finite%2Dstate+and+context%2Dfree+t) [our card](https://md.research.elamur.ai/free/en/papers/dyer-2010-cdec-decoder-alignment-learning-framework/)
15. K. Erk and S. Padó. 2008. A structured vector space model for word meaning in context. Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=K%2E+Erk+and+S%2E+Pado%CC%81%2E+2008%2E+A+structured+vector+space+model+for+word+meaning+in+context%2E+Proceedings+of+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/erk-2008-structured-vector-space-model-word/)
16. J. R. Firth. 1957. A synopsis of linguistic theory 1930-55. 1952-59:1–32. [find](https://scholar.google.com/scholar?q=J%2E+R%2E+Firth%2E+1957%2E+A+synopsis+of+linguistic+theory+1930%2D55%2E+1952%2D59%3A1%E2%80%9332%2E)
17. E. Grefenstette and M. Sadrzadeh. 2011. Experimental support for a categorical compositional distributional model of meaning. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=E%2E+Grefenstette+and+M%2E+Sadrzadeh%2E+2011%2E+Experimental+support+for+a+categorical+compositional+distributional+model+of+meaning%2E+In+Proceedings+of+EMNLP%2E)
18. A. Haghighi, P. Liang, T. Berg-Kirkpatrick, and D. Klein. 2008. Learning bilingual lexicons from monolingual corpora. In Proceedings of ACL-HLT. [find](https://scholar.google.com/scholar?q=A%2E+Haghighi%2C+P%2E+Liang%2C+T%2E+Berg%2DKirkpatrick%2C+and+D%2E+Klein%2E+2008%2E+Learning+bilingual+lexicons+from+monolingual+corpora%2E+In+Proceedings+of+ACL%2DHLT%2E) [our card](https://md.research.elamur.ai/free/en/papers/haghighi-2008-learning-bilingual-lexicons-monolingual-corpora/)
19. K. M. Hermann and P. Blunsom. 2013. The Role of Syntax in Vector Space Models of Compositional Semantics. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=K%2E+M%2E+Hermann+and+P%2E+Blunsom%2E+2013%2E+The+Role+of+Syntax+in+Vector+Space+Models+of+Compositional+Semantics%2E+In+Proceedings+of+ACL%2E)
20. K. M. Hermann and P. Blunsom. 2014. Multilingual Distributed Representations without Word Alignment. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=K%2E+M%2E+Hermann+and+P%2E+Blunsom%2E+2014%2E+Multilingual+Distributed+Representations+without+Word+Alignment%2E+In+Proceedings+of+ICLR%2E)
21. N. Kalchbrenner and P. Blunsom. 2013. Recurrent convolutional neural networks for discourse compositionality. Proceedings of the ACL Workshop on Continuous Vector Space Models and their Compositionality. [find](https://scholar.google.com/scholar?q=N%2E+Kalchbrenner+and+P%2E+Blunsom%2E+2013%2E+Recurrent+convolutional+neural+networks+for+discourse+compositionality%2E+Proceedings+of+the+ACL+Workshop+on+Continuous+Vector+Space+Models+and+their+Compositionali) [our card](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-convolutional-neural-networks-discourse/)
22. A. Klementiev, I. Titov, and B. Bhattarai. 2012. Inducing crosslingual distributed representations of words. In Proceedings of COLING. [find](https://scholar.google.com/scholar?q=A%2E+Klementiev%2C+I%2E+Titov%2C+and+B%2E+Bhattarai%2E+2012%2E+Inducing+crosslingual+distributed+representations+of+words%2E+In+Proceedings+of+COLING%2E) [our card](https://md.research.elamur.ai/free/en/papers/klementiev-2012-inducing-crosslingual-distributed-representations-words/)
23. P. Koehn. 2005. Europarl: A Parallel Corpus for Statistical Machine Translation. In Proceedings of the Machine Translation Summit. [find](https://scholar.google.com/scholar?q=P%2E+Koehn%2E+2005%2E+Europarl%3A+A+Parallel+Corpus+for+Statistical+Machine+Translation%2E+In+Proceedings+of+the+Machine+Translation+Summit%2E)
24. S. Lauly, A. Boulanger, and H. Larochelle. 2013. Learning multilingual word representations using a bag-of-words autoencoder. In Deep Learning Workshop at NIPS. [find](https://scholar.google.com/scholar?q=S%2E+Lauly%2C+A%2E+Boulanger%2C+and+H%2E+Larochelle%2E+2013%2E+Learning+multilingual+word+representations+using+a+bag%2Dof%2Dwords+autoencoder%2E+In+Deep+Learning+Workshop+at+NIPS%2E)
25. D. D. Lewis, Y. Yang, T. G. Rose, and F. Li. 2004. Rcv1: A new benchmark collection for text categorization research. Journal of Machine Learning Research, 5:361–397, December. [find](https://scholar.google.com/scholar?q=D%2E+D%2E+Lewis%2C+Y%2E+Yang%2C+T%2E+G%2E+Rose%2C+and+F%2E+Li%2E+2004%2E+Rcv1%3A+A+new+benchmark+collection+for+text+categorization+research%2E+Journal+of+Machine+Learning+Research%2C+5%3A361%E2%80%93397%2C+December%2E) [our card](https://md.research.elamur.ai/free/en/papers/lewis-2004-rcv1-benchmark-collection-text-categorization/)
26. A. K. McCallum. 2002. Mallet: A machine learning for language toolkit. [http://mallet.cs.umass.edu](http://mallet.cs.umass.edu). [↗](http://mallet.cs.umass.edu)
27. T. Mikolov, M. Karafiát, L. Burget, J. Černocký, and S. Khudanpur. 2010. Recurrent neural network based language model. In Proceedings of INTER-SPEECH. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+M%2E+Karafia%CC%81t%2C+L%2E+Burget%2C+J%2E+C%CC%8Cernocky%CC%81%2C+and+S%2E+Khudanpur%2E+2010%2E+Recurrent+neural+network+based+language+model%2E+In+Proceedings+of+INTER%2DSPEECH%2E)
28. T. Mikolov, K. Chen, G. Corrado, and J. Dean. 2013a. Efficient Estimation of Word Representations in Vector Space. CoRR. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+K%2E+Chen%2C+G%2E+Corrado%2C+and+J%2E+Dean%2E+2013a%2E+Efficient+Estimation+of+Word+Representations+in+Vector+Space%2E+CoRR%2E)
29. T. Mikolov, Q. V. Le, and I. Sutskever. 2013b. Exploiting Similarities among Languages for Machine Translation. CoRR. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+Q%2E+V%2E+Le%2C+and+I%2E+Sutskever%2E+2013b%2E+Exploiting+Similarities+among+Languages+for+Machine+Translation%2E+CoRR%2E)
30. J. Mitchell and M. Lapata. 2008. Vector-based models of semantic composition. In In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=J%2E+Mitchell+and+M%2E+Lapata%2E+2008%2E+Vector%2Dbased+models+of+semantic+composition%2E+In+In+Proceedings+of+ACL%2E)
31. A. Mnih and G. Hinton. 2009. A scalable hierarchical distributed language model. In Proceedings of NIPS. [find](https://scholar.google.com/scholar?q=A%2E+Mnih+and+G%2E+Hinton%2E+2009%2E+A+scalable+hierarchical+distributed+language+model%2E+In+Proceedings+of+NIPS%2E)
32. J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, and A. Y. Ng. 2011. Multimodal deep learning. In ICML. [find](https://scholar.google.com/scholar?q=J%2E+Ngiam%2C+A%2E+Khosla%2C+M%2E+Kim%2C+J%2E+Nam%2C+H%2E+Lee%2C+and+A%2E+Y%2E+Ng%2E+2011%2E+Multimodal+deep+learning%2E+In+ICML%2E)
33. D. Roy. 2003. Grounded spoken language acquisition: Experiments in word learning. IEEE Transactions on Multimedia, 5(2):197–209, June. [find](https://scholar.google.com/scholar?q=D%2E+Roy%2E+2003%2E+Grounded+spoken+language+acquisition%3A+Experiments+in+word+learning%2E+IEEE+Transactions+on+Multimedia%2C+5%282%29%3A197%E2%80%93209%2C+June%2E)
34. A. P. Sarath Chandar, M. K. Mitesh, B. Ravindran, V. Raykar, and A. Saha. 2013. Multilingual deep learning. In Deep Learning Workshop at NIPS. [find](https://scholar.google.com/scholar?q=A%2E+P%2E+Sarath+Chandar%2C+M%2E+K%2E+Mitesh%2C+B%2E+Ravindran%2C+V%2E+Raykar%2C+and+A%2E+Saha%2E+2013%2E+Multilingual+deep+learning%2E+In+Deep+Learning+Workshop+at+NIPS%2E)
35. R. Socher, J. Pennington, E. H. Huang, A. Y. Ng, and C. D. Manning. 2011. Semi-supervised recursive autoencoders for predicting sentiment distributions. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=R%2E+Socher%2C+J%2E+Pennington%2C+E%2E+H%2E+Huang%2C+A%2E+Y%2E+Ng%2C+and+C%2E+D%2E+Manning%2E+2011%2E+Semi%2Dsupervised+recursive+autoencoders+for+predicting+sentiment+distributions%2E+In+Proceedings+of+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/socher-2011-semi-supervised-recursive-autoencoders-predicting/)
36. R. Socher, B. Huval, C. D. Manning, and A. Y. Ng. 2012. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of EMNLP-CoNLL, pages 1201–1211. [find](https://scholar.google.com/scholar?q=R%2E+Socher%2C+B%2E+Huval%2C+C%2E+D%2E+Manning%2C+and+A%2E+Y%2E+Ng%2E+2012%2E+Semantic+compositionality+through+recursive+matrix%2Dvector+spaces%2E+In+Proceedings+of+EMNLP%2DCoNLL%2C+pages+1201%E2%80%931211%2E) [our card](https://md.research.elamur.ai/free/en/papers/socher-2012-semantic-compositionality-through-recursive-matrix/)
37. N. Srivastava and R. Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. In Proceedings of NIPS. [find](https://scholar.google.com/scholar?q=N%2E+Srivastava+and+R%2E+Salakhutdinov%2E+2012%2E+Multimodal+learning+with+deep+boltzmann+machines%2E+In+Proceedings+of+NIPS%2E)
38. J. Turian, L. Ratinov, and Y. Bengio. 2010. Word representations: a simple and general method for semi-supervised learning. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=J%2E+Turian%2C+L%2E+Ratinov%2C+and+Y%2E+Bengio%2E+2010%2E+Word+representations%3A+a+simple+and+general+method+for+semi%2Dsupervised+learning%2E+In+Proceedings+of+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/turian-2010-word-representations-simple-general-method/)
39. P. D. Turney. 2012. Domain and function: A dual-space model of semantic relations and compositions. Journal of Artificial Intelligence Research, 44:533– 585. [find](https://scholar.google.com/scholar?q=P%2E+D%2E+Turney%2E+2012%2E+Domain+and+function%3A+A+dual%2Dspace+model+of+semantic+relations+and+compositions%2E+Journal+of+Artificial+Intelligence+Research%2C+44%3A533%E2%80%93+585%2E)
40. W.-T. Yih, K. Toutanova, J. C. Platt, and C. Meek. 2011. Learning discriminative projections for text similarity measures. In Proceedings of CoNLL. [find](https://scholar.google.com/scholar?q=W%2E%2DT%2E+Yih%2C+K%2E+Toutanova%2C+J%2E+C%2E+Platt%2C+and+C%2E+Meek%2E+2011%2E+Learning+discriminative+projections+for+text+similarity+measures%2E+In+Proceedings+of+CoNLL%2E) [our card](https://md.research.elamur.ai/free/en/papers/yih-2011-learning-discriminative-projections-text-similarity/)
41. W. Y. Zou, R. Socher, D. Cer, and C. D. Manning. 2013. Bilingual word embeddings for phrase-based machine translation. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=W%2E+Y%2E+Zou%2C+R%2E+Socher%2C+D%2E+Cer%2C+and+C%2E+D%2E+Manning%2E+2013%2E+Bilingual+word+embeddings+for+phrase%2Dbased+machine+translation%2E+In+Proceedings+of+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/zou-2013-bilingual-word-embeddings-phrase-based/)