---
title: "Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks — He 2015"
description: "The authors propose a Siamese convolutional network with two weight-sharing branches. 2.14 accuracy. 44 references, cited by 69 papers here."
authors: ["Hua He", "Kevin Gimpel", "Jimmy Lin"]
year: 2015
venue: "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D15-1181/"
doi: "10.18653/v1/d15-1181"
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/he-2015-multi-perspective-sentence-similarity-modeling/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/he-2015-multi-perspective-sentence-similarity-modeling/)

[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/) / Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

# Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

**Authors:** [Hua He](https://md.research.elamur.ai/free/en/authors/hua-he/), [Kevin Gimpel](https://md.research.elamur.ai/free/en/authors/kevin-gimpel/) and [Jimmy Lin](https://md.research.elamur.ai/free/en/authors/jimmy-lin/) · **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/D15-1181/) · [PDF](https://aclanthology.org/D15-1181.pdf) · [DOI 10.18653/v1/d15-1181](https://doi.org/10.18653/v1/d15-1181) · [OpenAlex](https://openalex.org/W2251427843)

**Citations:** 378 citations (OpenAlex, 2026-10-14) · [69](https://md.research.elamur.ai/free/en/papers/he-2015-multi-perspective-sentence-similarity-modeling/cited-by/) in our library, of the 140,884 papers whose bibliographies we read

## Summary
The paper tackles sentence similarity: given two sentences, produce a score that can drive paraphrase detection or graded relatedness. Lexical and structural variability, plus small annotated datasets, make sparse hand-built features hard to use. The authors propose a Siamese convolutional network with two weight-sharing branches. Each branch encodes a sentence in several ways: holistic filters span whole word vectors, per-dimension filters act on single embedding dimensions, windows have several widths, and max, min and mean pooling are combined. A structured similarity layer then compares local regions of the two representations, not single flattened vectors. It uses cosine distance, L2 Euclidean distance and element-wise difference, and its output feeds a fully connected scorer. The model is tested on MSRP, SICK (SemEval-2014) and MSRVID (SemEval-2012 STS). It matches the dependency tree LSTM on SICK and beats the best SemEval-2012 system on MSRVID. On MSRP it outperforms the CNN of Yin and Schütze without their pretraining. It needs no WordNet or parser, which matters for low-resource languages and specialized domains.

## Key points
- On MSRVID the model reaches Pearson's r of 0.9090. The top SemEval-2012 STS submission (Šarić et al.) scored 0.8803, so the gain is nearly 3 points.
- On SICK it performs on par with the dependency/constituency tree LSTMs of Tai et al. (2015). It does this without parsers or POS taggers and uses the same sparse targets and KL loss.
- Inputs are pretrained word embeddings, including PARAGRAM, plus optional POS-tag embeddings. The embedding and POS inputs were used only for MSRP.
- The ablation removes 9 components one at a time and re-trains for every task. Every removal hurts. The largest drops come from removing cosine/L2 distances (−2.31 accuracy on MSRP, −0.0309 r on SICK). Flattening away the similarity layer also costs a lot (−1.90 on MSRP, −0.0288 on SICK, −0.0121 on MSRVID).
- Restricting window widths to only ws = 1 and ws = ∞ costs 2.14 accuracy points on MSRP.

## Interesting ideas
- **Per-dimension convolution next to holistic filters.** Some filters slide along a single embedding dimension, alongside the usual full-vector filters. This extracts finer-grained signal and could be added to any CNN text encoder with little effort.
- **Pooling as several views.** Running max, min and mean pooling in parallel keeps information that max pooling alone throws away. It is a cheap way to enrich representations when data is scarce.
- **Compare regions, not sentence vectors.** Matching outputs by filter type, window width and pooling (the "Horizontal" and "Vertical" comparisons) beats comparing two flat vectors. This idea could carry over to retrieval, QA matching or cross-lingual alignment.
- **Several distance functions as features.** Cosine, Euclidean distance and element-wise difference together feed the classifier. The ablation shows they complement each other, a reusable trick for any pairwise model.
- **Architecture engineering for small data.** The authors suggest that structured, multi-path designs may compensate for limited training data, while simpler and deeper networks might win with more data. This is useful guidance when building models for low-resource languages such as Ukrainian without parsers.

*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/)

## Institutions

- [University of Maryland, College Park](https://md.research.elamur.ai/free/en/universities/university-of-maryland-college-park/) — University, College Park, United States · 65 works · 21,800 citations
- [University of Waterloo](https://md.research.elamur.ai/free/en/universities/university-of-waterloo/) — University, Waterloo, Canada · 36 works · 11,969 citations
- [Toyota Technological Institute at Chicago](https://md.research.elamur.ai/free/en/universities/toyota-technological-institute-at-chicago/) — University, Chicago, United States · 22 works · 9,297 citations

## Cite

Cite as: Hua He, Kevin Gimpel and Jimmy Lin. 2015. Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks. Proceedings of the 2015 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{he2015multi,
  title = {{Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks}},
  author = {Hua He, Kevin Gimpel and Jimmy Lin},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1181},
  url = {https://doi.org/10.18653/v1/d15-1181}
}
```

- [← previous Bilingual Word Representations with Monolingual Quality in Mind](https://md.research.elamur.ai/free/en/papers/luong-2015-bilingual-word-representations-monolingual-quality/)
- [next → Harnessing Context Incongruity for Sarcasm Detection](https://md.research.elamur.ai/free/en/papers/joshi-2015-harnessing-context-incongruity-sarcasm-detection/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/)

## References

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

1. Eneko Agirre, Mona Diab, Daniel Cer, and Aitor Gonzalez-Agirre. 2012. SemEval-2012 task 6: a pilot on semantic textual similarity. In Proceedings of the First Joint Conference on Lexical and Computational Semantics, pages 385–393. [our card](https://md.research.elamur.ai/free/en/papers/agirre-2012-semeval-2012-task-6-pilot/)
2. Galen Andrew, Raman Arora, Jeff Bilmes, and Karen Livescu. 2013. Deep canonical correlation analysis. In Proceedings of the 30th International Conference on Machine Learning, pages 1247–1255. [find](https://scholar.google.com/scholar?q=Galen+Andrew%2C+Raman+Arora%2C+Jeff+Bilmes%2C+and+Karen+Livescu%2E+2013%2E+Deep+canonical+correlation+analysis%2E+In+Proceedings+of+the+30th+International+Conference+on+Machine+Learning%2C+pages+1247%E2%80%931255%2E)
3. Daniel Bär, Chris Biemann, Iryna Gurevych, and Torsten Zesch. 2012. UKP: computing semantic textual similarity by combining multiple content similarity measures. In Proceedings of the First Joint Conference on Lexical and Computational Semantics, pages 435–440. [our card](https://md.research.elamur.ai/free/en/papers/bar-2012-ukp-computing-semantic-textual-similarity/)
4. Islam Beltagy, Katrin Erk, and Raymond Mooney. 2014. Probabilistic soft logic for semantic textual similarity. Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics, pages 1210–1219. [find](https://scholar.google.com/scholar?q=Islam+Beltagy%2C+Katrin+Erk%2C+and+Raymond+Mooney%2E+2014%2E+Probabilistic+soft+logic+for+semantic+textual+similarity%2E+Proceedings+of+52nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+page)
5. Johannes Bjerva, Johan Bos, Rob van der Goot, and Malvina Nissim. 2014. The meaning factory: formal semantics for recognizing textual entailment and determining semantic similarity. International Workshop on Semantic Evaluation. [find](https://scholar.google.com/scholar?q=Johannes+Bjerva%2C+Johan+Bos%2C+Rob+van+der+Goot%2C+and+Malvina+Nissim%2E+2014%2E+The+meaning+factory%3A+formal+semantics+for+recognizing+textual+entailment+and+determining+semantic+similarity%2E+International+Work)
6. William Blacoe and Mirella Lapata. 2012. A comparison of vector-based representations for semantic composition. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 546–556. [our card](https://md.research.elamur.ai/free/en/papers/blacoe-2012-comparison-vector-based-representations-semantic/)
7. Léon Bottou. 1998. Online learning and stochastic approximations. On-line learning in neural networks, 17(9):142. [find](https://scholar.google.com/scholar?q=Le%CC%81on+Bottou%2E+1998%2E+Online+learning+and+stochastic+approximations%2E+On%2Dline+learning+in+neural+networks%2C+17%289%29%3A142%2E)
8. Jane Bromley, James W Bentz, Léon Bottou, Isabelle Guyon, Yann LeCun, Cliff Moore, Eduard Säckinger, and Roopak Shah. 1993. Signature verification using a “siamese” time delay neural network. International Journal of Pattern Recognition and Artificial Intelligence, 7(4):669–688. [find](https://scholar.google.com/scholar?q=Jane+Bromley%2C+James+W+Bentz%2C+Le%CC%81on+Bottou%2C+Isabelle+Guyon%2C+Yann+LeCun%2C+Cliff+Moore%2C+Eduard+Sa%CC%88ckinger%2C+and+Roopak+Shah%2E+1993%2E+Signature+verification+using+a+%E2%80%9Csiamese%E2%80%9D+time+delay+neural+network%2E+Intern)
9. Ronan Collobert and Jason Weston. 2008. A unified architecture for natural language processing: deep neural networks with multitask learning. In Proceedings of the 25th International Conference on Machine learning, pages 160–167. [find](https://scholar.google.com/scholar?q=Ronan+Collobert+and+Jason+Weston%2E+2008%2E+A+unified+architecture+for+natural+language+processing%3A+deep+neural+networks+with+multitask+learning%2E+In+Proceedings+of+the+25th+International+Conference+on+Mac)
10. Dipanjan Das and Noah A. Smith. 2009. Paraphrase identification as probabilistic quasi-synchronous recognition. In Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing… [our card](https://md.research.elamur.ai/free/en/papers/das-2009-paraphrase-identification-as-probabilistic-quasi/)
11. Bill Dolan, Chris Quirk, and Chris Brockett. 2004. Unsupervised construction of large paraphrase corpora: exploiting massively parallel news sources. In Proceedings of the 20th International Conference on Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/dolan-2004-unsupervised-construction-large-paraphrase-corpora/)
12. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. MIT Press. [find](https://scholar.google.com/scholar?q=Christiane+Fellbaum%2E+1998%2E+WordNet%3A+An+Electronic+Lexical+Database%2E+MIT+Press%2E)
13. Samuel Fern and Mark Stevenson. 2008. A semantic similarity approach to paraphrase detection. In Computational Linguistics UK 11th Annual Research Colloquium. [find](https://scholar.google.com/scholar?q=Samuel+Fern+and+Mark+Stevenson%2E+2008%2E+A+semantic+similarity+approach+to+paraphrase+detection%2E+In+Computational+Linguistics+UK+11th+Annual+Research+Colloquium%2E)
14. Andrew Finch. 2005. Using machine translation evaluation techniques to determine sentence-level semantic equivalence. In Proceedings of the International Workshop on Paraphrasing. [find](https://scholar.google.com/scholar?q=Andrew+Finch%2E+2005%2E+Using+machine+translation+evaluation+techniques+to+determine+sentence%2Dlevel+semantic+equivalence%2E+In+Proceedings+of+the+International+Workshop+on+Paraphrasing%2E)
15. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: the Paraphrase Database. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [our card](https://md.research.elamur.ai/free/en/papers/ganitkevitch-2013-ppdb-paraphrase-database/)
16. Christoph Goller and Andreas Kuchler. 1996. Learning task-dependent distributed representations by backpropagation through structure. In Proceedings of the International Conference on Neural Networks, pages 347–352. [find](https://scholar.google.com/scholar?q=Christoph+Goller+and+Andreas+Kuchler%2E+1996%2E+Learning+task%2Ddependent+distributed+representations+by+backpropagation+through+structure%2E+In+Proceedings+of+the+International+Conference+on+Neural+Networks%2C)
17. Weiwei Guo and Mona Diab. 2012. Modeling sentences in the latent space. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 864–872. [find](https://scholar.google.com/scholar?q=Weiwei+Guo+and+Mona+Diab%2E+2012%2E+Modeling+sentences+in+the+latent+space%2E+In+Proceedings+of+the+50th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+864%E2%80%93872%2E)
18. Samer Hassan. 2011. Measuring Semantic Relatedness Using Salient Encyclopedic Concepts. Ph.D. thesis, University of North Texas, Denton, Texas, USA. [find](https://scholar.google.com/scholar?q=Samer+Hassan%2E+2011%2E+Measuring+Semantic+Relatedness+Using+Salient+Encyclopedic+Concepts%2E+Ph%2ED%2E+thesis%2C+University+of+North+Texas%2C+Denton%2C+Texas%2C+USA%2E)
19. Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In Advances in Neural Information Processing Systems, pages 2042–2050. [find](https://scholar.google.com/scholar?q=Baotian+Hu%2C+Zhengdong+Lu%2C+Hang+Li%2C+and+Qingcai+Chen%2E+2014%2E+Convolutional+neural+network+architectures+for+matching+natural+language+sentences%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pag)
20. Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, pages 2333–2338. [find](https://scholar.google.com/scholar?q=Po%2DSen+Huang%2C+Xiaodong+He%2C+Jianfeng+Gao%2C+Li+Deng%2C+Alex+Acero%2C+and+Larry+Heck%2E+2013%2E+Learning+deep+structured+semantic+models+for+web+search+using+clickthrough+data%2E+In+Proceedings+of+the+22nd+ACM+Inte)
21. Yangfeng Ji and Jacob Eisenstein. 2013. Discriminative improvements to distributional sentence similarity. In Proceedings of the 2013 Conference on Empirical Methods for Natural Language Processing, pages 891–896. [find](https://scholar.google.com/scholar?q=Yangfeng+Ji+and+Jacob+Eisenstein%2E+2013%2E+Discriminative+improvements+to+distributional+sentence+similarity%2E+In+Proceedings+of+the+2013+Conference+on+Empirical+Methods+for+Natural+Language+Processing%2C+p)
22. Sergio Jimenez, George Duenas, Julia Baquero, Alexander Gelbukh, Av Juan Dios Bátiz, and Av Mendizábal. 2014. UNAL-NLP: combining soft cardinality features for semantic textual similarity, relatedness and entailment. International Workshop on Semantic Evaluation. [find](https://scholar.google.com/scholar?q=Sergio+Jimenez%2C+George+Duenas%2C+Julia+Baquero%2C+Alexander+Gelbukh%2C+Av+Juan+Dios+Ba%CC%81tiz%2C+and+Av+Mendiza%CC%81bal%2E+2014%2E+UNAL%2DNLP%3A+combining+soft+cardinality+features+for+semantic+textual+similarity%2C+relatedne)
23. Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A convolutional neural network for modelling sentences. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2014-convolutional-neural-network-modelling-sentences/)
24. Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods for Natural Language Processing. [our card](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/)
25. Alice Lai and Julia Hockenmaier. 2014. Illinois-LH: a denotational and distributional approach to semantics. International Workshop on Semantic Evaluation. [find](https://scholar.google.com/scholar?q=Alice+Lai+and+Julia+Hockenmaier%2E+2014%2E+Illinois%2DLH%3A+a+denotational+and+distributional+approach+to+semantics%2E+International+Workshop+on+Semantic+Evaluation%2E)
26. Nitin Madnani, Joel Tetreault, and Martin Chodorow. 2012. Re-examining machine translation metrics for paraphrase identification. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 182–190. [our card](https://md.research.elamur.ai/free/en/papers/madnani-2012-re-examining-machine-translation-metrics/)
27. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60. [our card](https://md.research.elamur.ai/free/en/papers/manning-2014-stanford-corenlp-natural-language-processing/)
28. Marco Marelli, Luisa Bentivogli, Marco Baroni, Raffaella Bernardi, Stefano Menini, and Roberto Zamparelli. 2014. SemEval-2014 task 1: evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment. International Workshop on Semantic E… [our card](https://md.research.elamur.ai/free/en/papers/marelli-2014-semeval-2014-task-1-evaluation/)
29. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. Proceedings of Workshop at International Conference on Learning Representations. [our card](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/)
30. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1532–1543. [our card](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/)
31. Steven Rennie, Vaibhava Goel, and Samuel Thomas. 2014. Deep order statistic networks. In Proceedings of the IEEE Workshop on Spoken Language Technology. [find](https://scholar.google.com/scholar?q=Steven+Rennie%2C+Vaibhava+Goel%2C+and+Samuel+Thomas%2E+2014%2E+Deep+order+statistic+networks%2E+In+Proceedings+of+the+IEEE+Workshop+on+Spoken+Language+Technology%2E)
32. Miguel Rios, Wilker Aziz, and Lucia Specia. 2012. UOW: semantically informed text similarity. In Proceedings of the First Joint Conference on Lexical and Computational Semantics, pages 673–678. [find](https://scholar.google.com/scholar?q=Miguel+Rios%2C+Wilker+Aziz%2C+and+Lucia+Specia%2E+2012%2E+UOW%3A+semantically+informed+text+similarity%2E+In+Proceedings+of+the+First+Joint+Conference+on+Lexical+and+Computational+Semantics%2C+pages+673%E2%80%93678%2E)
33. Frane Šarić, Goran Glavaš, Mladen Karan, Jan Šnajder, and Bojana Dalbelo Bašić. 2012. TakeLab: systems for measuring semantic text similarity. In Proceedings of the First Joint Conference on Lexical and Computational Semantics, pages 441–448. [find](https://scholar.google.com/scholar?q=Frane+S%CC%8Caric%CC%81%2C+Goran+Glavas%CC%8C%2C+Mladen+Karan%2C+Jan+S%CC%8Cnajder%2C+and+Bojana+Dalbelo+Bas%CC%8Cic%CC%81%2E+2012%2E+TakeLab%3A+systems+for+measuring+semantic+text+similarity%2E+In+Proceedings+of+the+First+Joint+Conference+on+Lex)
34. Richard Socher, Eric H. Huang, Jeffrey Pennington, Andrew Y. Ng, and Christopher D. Manning. 2011. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. In Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Eric+H%2E+Huang%2C+Jeffrey+Pennington%2C+Andrew+Y%2E+Ng%2C+and+Christopher+D%2E+Manning%2E+2011%2E+Dynamic+pooling+and+unfolding+recursive+autoencoders+for+paraphrase+detection%2E+In+Advances+in+Neural+)
35. Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, and Andrew Y. Ng. 2014. Grounded compositional semantics for finding and describing images with sentences. Transactions of the Association for Computational Linguistics, 2:207–218. [our card](https://md.research.elamur.ai/free/en/papers/socher-2014-grounded-compositional-semantics-finding-describing/)
36. Kai Sheng Tai, Richard Socher, and Christopher D. Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kai+Sheng+Tai%2C+Richard+Socher%2C+and+Christopher+D%2E+Manning%2E+2015%2E+Improved+semantic+representations+from+tree%2Dstructured+long+short%2Dterm+memory+networks%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+th)
37. Stephen Wan, Mark Dras, Robert Dale, and Cecile Paris. 2006. Using Dependency-based Features to Take the ”Para-farce” out of Paraphrase. In Australasian Language Technology Workshop, pages 131–138. [find](https://scholar.google.com/scholar?q=Stephen+Wan%2C+Mark+Dras%2C+Robert+Dale%2C+and+Cecile+Paris%2E+2006%2E+Using+Dependency%2Dbased+Features+to+Take+the+%E2%80%9DPara%2Dfarce%E2%80%9D+out+of+Paraphrase%2E+In+Australasian+Language+Technology+Workshop%2C+pages+131%E2%80%93138%2E)
38. Mengqiu Wang and Daniel Cer. 2012. Probabilistic edit distance metrics for STS. In Proceedings of the First Joint Conference on Lexical and Computational Semantics, pages 648–654. [find](https://scholar.google.com/scholar?q=Mengqiu+Wang+and+Daniel+Cer%2E+2012%2E+Probabilistic+edit+distance+metrics+for+STS%2E+In+Proceedings+of+the+First+Joint+Conference+on+Lexical+and+Computational+Semantics%2C+pages+648%E2%80%93654%2E)
39. Jason Weston, Samy Bengio, and Nicolas Usunier. 2011. Wsabie: scaling up to large vocabulary image annotation. In International Joint Conference on Artificial Intelligence, pages 2764–2770. [find](https://scholar.google.com/scholar?q=Jason+Weston%2C+Samy+Bengio%2C+and+Nicolas+Usunier%2E+2011%2E+Wsabie%3A+scaling+up+to+large+vocabulary+image+annotation%2E+In+International+Joint+Conference+on+Artificial+Intelligence%2C+pages+2764%E2%80%932770%2E)
40. John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu, and Dan Roth. 2015. From paraphrase database to compositional paraphrase model and back. Transactions of the Association for Computational Linguistics, 3:345–358. [our card](https://md.research.elamur.ai/free/en/papers/wieting-2015-paraphrase-database-compositional-paraphrase-model/)
41. Wei Xu, Alan Ritter, Chris Callison-Burch, William B. Dolan, and Yangfeng Ji. 2014. Extracting lexically divergent paraphrases from Twitter. Transactions of the Association for Computational Linguistics, 2:435–448. [find](https://scholar.google.com/scholar?q=Wei+Xu%2C+Alan+Ritter%2C+Chris+Callison%2DBurch%2C+William+B%2E+Dolan%2C+and+Yangfeng+Ji%2E+2014%2E+Extracting+lexically+divergent+paraphrases+from+Twitter%2E+Transactions+of+the+Association+for+Computational+Linguisti)
42. Wenpeng Yin and Hinrich Schütze. 2015. Convolutional neural network for paraphrase identification. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 901–911. [find](https://scholar.google.com/scholar?q=Wenpeng+Yin+and+Hinrich+Schu%CC%88tze%2E+2015%2E+Convolutional+neural+network+for+paraphrase+identification%2E+In+Proceedings+of+the+2015+Conference+of+the+North+American+Chapter+of+the+Association+for+Computati)
43. Jiang Zhao, Tian Tian Zhu, and Man Lan. 2014. ECNU: one stone two birds: ensemble of heterogenous measures for semantic relatedness and textual entailment. International Workshop on Semantic Evaluation. [find](https://scholar.google.com/scholar?q=Jiang+Zhao%2C+Tian+Tian+Zhu%2C+and+Man+Lan%2E+2014%2E+ECNU%3A+one+stone+two+birds%3A+ensemble+of+heterogenous+measures+for+semantic+relatedness+and+textual+entailment%2E+International+Workshop+on+Semantic+Evaluatio)
44. Xiaodan Zhu, Parinaz Sobhani, and Hongyu Guo. 2015. Long short-term memory over recursive structures. In Proceedings of the 32nd International Conference on Machine Learning, pages 1604– 1612. [find](https://scholar.google.com/scholar?q=Xiaodan+Zhu%2C+Parinaz+Sobhani%2C+and+Hongyu+Guo%2E+2015%2E+Long+short%2Dterm+memory+over+recursive+structures%2E+In+Proceedings+of+the+32nd+International+Conference+on+Machine+Learning%2C+pages+1604%E2%80%93+1612%2E)