---
title: "Recursive Deep Models for Semantic Compositionality Over a"
description: "Vectors of individual words poorly capture the meaning of longer phrases. 44 references, cited by 2,591 papers here."
authors: ["Richard Socher", "Alex Perelygin", "Jean Wu", "Jason Chuang", "Christopher D. Manning", "Andrew Ng", "Christopher Potts"]
year: 2013
venue: "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D13-1170/"
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/socher-2013-recursive-deep-models-semantic-compositionality/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/) / Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

# Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

**Authors:** [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/), Alex Perelygin, [Jean Wu](https://md.research.elamur.ai/free/en/authors/jean-y-wu/), Jason Chuang, [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/), [Andrew Ng](https://md.research.elamur.ai/free/en/authors/andrew-ng/) and [Christopher Potts](https://md.research.elamur.ai/free/en/authors/christopher-e-potts/) · **Year:** 2013 · **Venue:** [Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2013](https://md.research.elamur.ai/free/en/venues/emnlp/2013/)) · **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/D13-1170/) · [PDF](https://aclanthology.org/D13-1170.pdf) · [OpenAlex](https://openalex.org/W2251939518)

**Citations:** 6,547 citations (OpenAlex, 2026-10-14) · [2591](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Vectors of individual words poorly capture the meaning of longer phrases. Studying how the sentiment of a sentence is composed from its parts was hampered by a lack of large annotated resources. The authors created the Stanford Sentiment Treebank. They took a corpus of short movie review excerpts from rottentomatoes.com (Pang and Lee, 2005) and parsed the sentences with the Stanford Parser. They then used Amazon Mechanical Turk to collect sentiment ratings for every phrase in the resulting trees. They also proposed the Recursive Neural Tensor Network (RNTN). This recursive model computes the vectors of a binary tree's nodes bottom-up and uses a single shared tensor-based composition function for all nodes. RNTN was compared with RNN, MV-RNN, Naive Bayes, SVM and other baseline models, and it achieved the best results. In binary sentence classification, accuracy rose from roughly 80% to 85.4%. In five-class prediction over all phrases, it reached 80.7%. In addition, the model correctly captures the effect of negation and the scope of its influence. The work gave the community a resource with phrase-level annotation and showed that models that take syntactic structure into account outperform bag-of-words approaches.

## Key points
- **Treebank size:** 11,855 sentences and 215,154 unique phrases. Each phrase was rated by 3 annotators. They used a slider with 25 positions, which were later collapsed into 5 classes: from very negative to very positive.
- **Rating distribution:** short n-grams are mostly neutral. Strong sentiment appears mainly in longer phrases.
- **Accuracy:** in binary sentence classification, it rose from roughly 80% to 85.4%. In fine-grained prediction over all phrases, the result is 80.7%, which is 9.7% better than bag-of-features baselines.
- **Negation:** for negations of positive sentences, RNTN correctly reverses the sentiment in 71.4% of cases. For negations of negative sentences, it increases the positive activation in 81.8% of cases. For comparison, the corresponding figures for biNB are 19.0% and 27.3%.
- **The conjunction "but" and availability:** the model learns that in a sentence with "but", the sentiment of the part after the conjunction dominates. The code, an online demo and the corpus are published at nlp.stanford.edu/sentiment.

*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

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 434 works · 314,419 citations
- [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 353 works · 200,043 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works · [🗂️ Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) · 126 works

💡 Concepts (2): [💡 Natural language processing](https://md.research.elamur.ai/free/en/concepts/natural-language-processing/) · 131 works · [💡 Semantics](https://md.research.elamur.ai/free/en/concepts/semantics/) · 57 works

## Cite

Cite as: Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{socher2013recursive,
  title = {{Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank}},
  author = {Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng and Christopher Potts},
  booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing},
  year = {2013},
  doi = {10.18653/v1/d13-1170},
  url = {https://doi.org/10.18653/v1/d13-1170}
}
```

- [← previous Auto-Encoding Variational Bayes](https://md.research.elamur.ai/free/en/papers/kingma-2013-auto-encoding-variational-bayes/)
- [next → Intriguing properties of neural networks](https://md.research.elamur.ai/free/en/papers/szegedy-2013-intriguing-properties-neural-networks/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/)

## References

44 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. M. Baroni and A. Lenci. 2010. [Distributional memory: A general framework for corpus-based semantics](https://md.research.elamur.ai/free/en/papers/baroni-2010-distributional-memory-general-framework-corpus/). Computational Linguistics, 36(4):673–721.
2. Y. Bengio, R. Ducharme, P. Vincent, and C. Janvin. 2003. [A neural probabilistic language model](https://md.research.elamur.ai/free/en/papers/bengio-2003-neural-probabilistic-language-model/). J. Mach. Learn. Res., 3, March.
3. D. Blakemore. 1989. Denial and contrast: A relevance theoretic analysis of ‘but’. Linguistics and Philosophy, 12:15–37. [find](https://scholar.google.com/scholar?q=D%2E+Blakemore%2E+1989%2E+Denial+and+contrast%3A+A+relevance+theoretic+analysis+of+%E2%80%98but%E2%80%99%2E+Linguistics+and+Philosophy%2C+12%3A15%E2%80%9337%2E)
4. L. Bottou. 2011. From machine learning to machine reasoning. CoRR, abs/1102.1808. — [arXiv:1102.1808](https://arxiv.org/abs/1102.1808) [find](https://scholar.google.com/scholar?q=L%2E+Bottou%2E+2011%2E+From+machine+learning+to+machine+reasoning%2E+CoRR%2C+abs%2F1102%2E1808%2E+%E2%80%94+%5BarXiv%3A1102%2E1808%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1102%2E1808%29)
5. S. Clark and S. Pulman. 2007. Combining symbolic and distributional models of meaning. In Proceedings of the AAAI Spring Symposium on Quantum Interaction, pages 52–55. [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+the+AAAI+Spring+Symposium+on+Quantum+Interaction%2C+pages+52%E2%80%9355%2E)
6. R. Collobert and J. Weston. 2008. A unified architecture for natural language processing: deep neural networks with multitask learning. In 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+ICML%2E)
7. J. Duchi, E. Hazan, and Y. Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. JMLR, 12, 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+JMLR%2C+12%2C+July%2E)
8. K. Erk and S. Padó. 2008. [A structured vector space model for word meaning in context](https://md.research.elamur.ai/free/en/papers/erk-2008-structured-vector-space-model-word/). In EMNLP.
9. C. Goller and A. Küchler. 1996. Learning task-dependent distributed representations by backpropagation through structure. In Proceedings of the International Conference on Neural Networks (ICNN-96). [find](https://scholar.google.com/scholar?q=C%2E+Goller+and+A%2E+Ku%CC%88chler%2E+1996%2E+Learning+task%2Ddependent+distributed+representations+by+backpropagation+through+structure%2E+In+Proceedings+of+the+International+Conference+on+Neural+Networks+%28ICNN%2D96%29%2E)
10. E. Grefenstette and M. Sadrzadeh. 2011. Experimental support for a categorical compositional distributional model of meaning. In 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+EMNLP%2E)
11. E. Grefenstette, G. Dinu, Y.-Z. Zhang, M. Sadrzadeh, and M. Baroni. 2013. Multi-step regression learning for compositional distributional semantics. In IWCS. [find](https://scholar.google.com/scholar?q=E%2E+Grefenstette%2C+G%2E+Dinu%2C+Y%2E%2DZ%2E+Zhang%2C+M%2E+Sadrzadeh%2C+and+M%2E+Baroni%2E+2013%2E+Multi%2Dstep+regression+learning+for+compositional+distributional+semantics%2E+In+IWCS%2E)
12. G. E. Hinton. 1990. Mapping part-whole hierarchies into connectionist networks. Artificial Intelligence, 46(1-2). [find](https://scholar.google.com/scholar?q=G%2E+E%2E+Hinton%2E+1990%2E+Mapping+part%2Dwhole+hierarchies+into+connectionist+networks%2E+Artificial+Intelligence%2C+46%281%2D2%29%2E)
13. L. R. Horn. 1989. A natural history of negation, volume 960. University of Chicago Press Chicago. [find](https://scholar.google.com/scholar?q=L%2E+R%2E+Horn%2E+1989%2E+A+natural+history+of+negation%2C+volume+960%2E+University+of+Chicago+Press+Chicago%2E)
14. E. H. Huang, R. Socher, C. D. Manning, and A. Y. Ng. 2012. [Improving Word Representations via Global Context and Multiple Word Prototypes](https://md.research.elamur.ai/free/en/papers/huang-2012-improving-word-representations-global-context/). In ACL.
15. M. Israel. 2001. Minimizers, maximizers, and the rhetoric of scalar reasoning. Journal of Semantics, 18(4):297–331. [find](https://scholar.google.com/scholar?q=M%2E+Israel%2E+2001%2E+Minimizers%2C+maximizers%2C+and+the+rhetoric+of+scalar+reasoning%2E+Journal+of+Semantics%2C+18%284%29%3A297%E2%80%93331%2E)
16. R. Jenatton, N. Le Roux, A. Bordes, and G. Obozinski. 2012. A latent factor model for highly multi-relational data. In NIPS. [find](https://scholar.google.com/scholar?q=R%2E+Jenatton%2C+N%2E+Le+Roux%2C+A%2E+Bordes%2C+and+G%2E+Obozinski%2E+2012%2E+A+latent+factor+model+for+highly+multi%2Drelational+data%2E+In+NIPS%2E)
17. D. Klein and C. D. Manning. 2003. [Accurate unlexicalized parsing](https://md.research.elamur.ai/free/en/papers/klein-2003-accurate-unlexicalized-parsing/). In ACL.
18. R. Lakoff. 1971. If’s, and’s, and but’s about conjunction. In Charles J. Fillmore and D. Terence Langendoen, editors, Studies in Linguistic Semantics, pages 114–149. Holt, Rinehart, and Winston, New York. [find](https://scholar.google.com/scholar?q=R%2E+Lakoff%2E+1971%2E+If%E2%80%99s%2C+and%E2%80%99s%2C+and+but%E2%80%99s+about+conjunction%2E+In+Charles+J%2E+Fillmore+and+D%2E+Terence+Langendoen%2C+editors%2C+Studies+in+Linguistic+Semantics%2C+pages+114%E2%80%93149%2E+Holt%2C+Rinehart%2C+and+Winston%2C+New+Y)
19. A. Merin. 1999. Information, relevance, and social decisionmaking: Some principles and results of decision-theoretic semantics. In Lawrence S. Moss, Jonathan Ginzburg, and Maarten de Rijke, editors, Logic, Language, and Information, volume 2. CSLI, Stanford, CA. [find](https://scholar.google.com/scholar?q=A%2E+Merin%2E+1999%2E+Information%2C+relevance%2C+and+social+decisionmaking%3A+Some+principles+and+results+of+decision%2Dtheoretic+semantics%2E+In+Lawrence+S%2E+Moss%2C+Jonathan+Ginzburg%2C+and+Maarten+de+Rijke%2C+editors%2C+L)
20. J. Mitchell and M. Lapata. 2010. Composition in distributional models of semantics. Cognitive Science, 34(8):1388–1429. [find](https://scholar.google.com/scholar?q=J%2E+Mitchell+and+M%2E+Lapata%2E+2010%2E+Composition+in+distributional+models+of+semantics%2E+Cognitive+Science%2C+34%288%29%3A1388%E2%80%931429%2E)
21. K. Moilanen and S. Pulman. 2007. Sentiment composition. In In Proceedings of Recent Advances in Natural Language Processing. [find](https://scholar.google.com/scholar?q=K%2E+Moilanen+and+S%2E+Pulman%2E+2007%2E+Sentiment+composition%2E+In+In+Proceedings+of+Recent+Advances+in+Natural+Language+Processing%2E)
22. T. Nakagawa, K. Inui, and S. Kurohashi. 2010. [Dependency tree-based sentiment classification using CRFs with hidden variables](https://md.research.elamur.ai/free/en/papers/nakagawa-2010-dependency-tree-based-sentiment-classification/). In NAACL, HLT.
23. S. Pado and M. Lapata. 2007. [Dependency-based construction of semantic space models](https://md.research.elamur.ai/free/en/papers/pado-2007-dependency-based-construction-semantic-space/). Computational Linguistics, 33(2):161–199.
24. B. Pang and L. Lee. 2005. [Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales](https://md.research.elamur.ai/free/en/papers/pang-2005-seeing-stars-exploiting-class-relationships/). In ACL, pages 115–124.
25. B. Pang and L. Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2):1–135. [find](https://scholar.google.com/scholar?q=B%2E+Pang+and+L%2E+Lee%2E+2008%2E+Opinion+mining+and+sentiment+analysis%2E+Foundations+and+Trends+in+Information+Retrieval%2C+2%281%2D2%29%3A1%E2%80%93135%2E)
26. T. A. Plate. 1995. Holographic reduced representations. IEEE Transactions on Neural Networks, 6(3):623– 641. [find](https://scholar.google.com/scholar?q=T%2E+A%2E+Plate%2E+1995%2E+Holographic+reduced+representations%2E+IEEE+Transactions+on+Neural+Networks%2C+6%283%29%3A623%E2%80%93+641%2E)
27. L. Polanyi and A. Zaenen. 2006. Contextual valence shifters. In W. Bruce Croft, James Shanahan, Yan Qu, and Janyce Wiebe, editors, Computing Attitude and Affect in Text: Theory and Applications, volume 20 of The Information Retrieval Series, chapter 1. [find](https://scholar.google.com/scholar?q=L%2E+Polanyi+and+A%2E+Zaenen%2E+2006%2E+Contextual+valence+shifters%2E+In+W%2E+Bruce+Croft%2C+James+Shanahan%2C+Yan+Qu%2C+and+Janyce+Wiebe%2C+editors%2C+Computing+Attitude+and+Affect+in+Text%3A+Theory+and+Applications%2C+volum)
28. J. B. Pollack. 1990. Recursive distributed representations. Artificial Intelligence, 46, November. [find](https://scholar.google.com/scholar?q=J%2E+B%2E+Pollack%2E+1990%2E+Recursive+distributed+representations%2E+Artificial+Intelligence%2C+46%2C+November%2E)
29. M. Ranzato and A. Krizhevsky G. E. Hinton. 2010. Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images. AISTATS. [find](https://scholar.google.com/scholar?q=M%2E+Ranzato+and+A%2E+Krizhevsky+G%2E+E%2E+Hinton%2E+2010%2E+Factored+3%2DWay+Restricted+Boltzmann+Machines+For+Modeling+Natural+Images%2E+AISTATS%2E)
30. V. Rentoumi, S. Petrakis, M. Klenner, G. A. Vouros, and V. Karkaletsis. 2010. United we stand: Improving sentiment analysis by joining machine learning and rule based methods. In Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC’10), Valletta, Malta. [find](https://scholar.google.com/scholar?q=V%2E+Rentoumi%2C+S%2E+Petrakis%2C+M%2E+Klenner%2C+G%2E+A%2E+Vouros%2C+and+V%2E+Karkaletsis%2E+2010%2E+United+we+stand%3A+Improving+sentiment+analysis+by+joining+machine+learning+and+rule+based+methods%2E+In+Proceedings+of+the+Se)
31. S. Rudolph and E. Giesbrecht. 2010. Compositional matrix-space models of language. In ACL. [find](https://scholar.google.com/scholar?q=S%2E+Rudolph+and+E%2E+Giesbrecht%2E+2010%2E+Compositional+matrix%2Dspace+models+of+language%2E+In+ACL%2E)
32. B. Snyder and R. Barzilay. 2007. Multiple aspect ranking using the Good Grief algorithm. In HLT-NAACL. [find](https://scholar.google.com/scholar?q=B%2E+Snyder+and+R%2E+Barzilay%2E+2007%2E+Multiple+aspect+ranking+using+the+Good+Grief+algorithm%2E+In+HLT%2DNAACL%2E)
33. R. Socher, C. D. Manning, and A. Y. Ng. 2010. Learning continuous phrase representations and syntactic parsing with recursive neural networks. In Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop. [find](https://scholar.google.com/scholar?q=R%2E+Socher%2C+C%2E+D%2E+Manning%2C+and+A%2E+Y%2E+Ng%2E+2010%2E+Learning+continuous+phrase+representations+and+syntactic+parsing+with+recursive+neural+networks%2E+In+Proceedings+of+the+NIPS%2D2010+Deep+Learning+and+Unsuper)
34. R. Socher, C. Lin, A. Y. Ng, and C.D. Manning. 2011a. Parsing Natural Scenes and Natural Language with Recursive Neural Networks. In ICML. [find](https://scholar.google.com/scholar?q=R%2E+Socher%2C+C%2E+Lin%2C+A%2E+Y%2E+Ng%2C+and+C%2ED%2E+Manning%2E+2011a%2E+Parsing+Natural+Scenes+and+Natural+Language+with+Recursive+Neural+Networks%2E+In+ICML%2E)
35. R. Socher, J. Pennington, E. H. Huang, A. Y. Ng, and C. D. Manning. 2011b. [Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions](https://md.research.elamur.ai/free/en/papers/socher-2011-semi-supervised-recursive-autoencoders-predicting/). In EMNLP.
36. R. Socher, B. Huval, C. D. Manning, and A. Y. Ng. 2012. [Semantic compositionality through recursive matrix-vector spaces](https://md.research.elamur.ai/free/en/papers/socher-2012-semantic-compositionality-through-recursive-matrix/). In EMNLP.
37. I. Sutskever, R. Salakhutdinov, and J. B. Tenenbaum. 2009. Modelling relational data using Bayesian clustered tensor factorization. In NIPS. [find](https://scholar.google.com/scholar?q=I%2E+Sutskever%2C+R%2E+Salakhutdinov%2C+and+J%2E+B%2E+Tenenbaum%2E+2009%2E+Modelling+relational+data+using+Bayesian+clustered+tensor+factorization%2E+In+NIPS%2E)
38. P. D. Turney and P. Pantel. 2010. [From frequency to meaning: Vector space models of semantics](https://md.research.elamur.ai/free/en/papers/turney-2010-frequency-meaning-vector-space-models/). Journal of Artificial Intelligence Research, 37:141–188.
39. H. Wang, D. Can, A. Kazemzadeh, F. Bar, and S. Narayanan. 2012. A system for real-time twitter sentiment analysis of 2012 u.s. presidential election cycle. In Proceedings of the ACL 2012 System Demonstrations. [find](https://scholar.google.com/scholar?q=H%2E+Wang%2C+D%2E+Can%2C+A%2E+Kazemzadeh%2C+F%2E+Bar%2C+and+S%2E+Narayanan%2E+2012%2E+A+system+for+real%2Dtime+twitter+sentiment+analysis+of+2012+u%2Es%2E+presidential+election+cycle%2E+In+Proceedings+of+the+ACL+2012+System+Demons)
40. D. Widdows. 2008. Semantic vector products: Some initial investigations. In Proceedings of the Second AAAI Symposium on Quantum Interaction. [find](https://scholar.google.com/scholar?q=D%2E+Widdows%2E+2008%2E+Semantic+vector+products%3A+Some+initial+investigations%2E+In+Proceedings+of+the+Second+AAAI+Symposium+on+Quantum+Interaction%2E)
41. A. Yessenalina and C. Cardie. 2011. Compositional matrix-space models for sentiment analysis. In EMNLP. [find](https://scholar.google.com/scholar?q=A%2E+Yessenalina+and+C%2E+Cardie%2E+2011%2E+Compositional+matrix%2Dspace+models+for+sentiment+analysis%2E+In+EMNLP%2E)
42. D. Yu, L. Deng, and F. Seide. 2012. Large vocabulary speech recognition using deep tensor neural networks. In INTERSPEECH. [find](https://scholar.google.com/scholar?q=D%2E+Yu%2C+L%2E+Deng%2C+and+F%2E+Seide%2E+2012%2E+Large+vocabulary+speech+recognition+using+deep+tensor+neural+networks%2E+In+INTERSPEECH%2E)
43. F.M. Zanzotto, I. Korkontzelos, F. Fallucchi, and S. Manandhar. 2010. [Estimating linear models for compositional distributional semantics](https://md.research.elamur.ai/free/en/papers/zanzotto-2010-estimating-linear-models-compositional-distributional/). In COLING.
44. L. Zettlemoyer and M. Collins. 2005. [Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars](https://md.research.elamur.ai/free/en/papers/zettlemoyer-2012-learning-map-sentences-logical-form/). In UAI.

*Updated 29 October 2026*