Abstract
Semantic textual similarity algorithms are essential to several natural language processing tasks as clustering documents and text summarization. Many shared tasks regarding this subject were performed during the last few years, but generally, focused on a unique domain and/or language. Siamese Neural Network (SNN) is well known for its ability to compute similarity requiring less training data. We proposed a SNN architecture incorporated with language-independent features, aiming to perform short text similarity calculation in multiple languages and domains. We explored three different corpora from shared tasks: ASSIN 1 and ASSIN 2 with Portuguese journalistic texts and N2C2 (English clinical texts). We adapted the SNN proposed by Mueller and Thyagarajan (2016), in two ways: (i) the activation functions were changed to the ReLU, instead of the sigmoid function, and; (ii) we incorporated the architecture to accept three new lexical features and an embedding layer to infer the values of the pre-trained word embeddings. The evaluation was performed by the Pearson correlation (PC) and the Mean Squared Error (MSE) between the models’ predicted values and corpora’s gold standard. Our approach achieved better results than the baseline in both languages and domains.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agirre, E., Cer, D., Diab, M., Gonzalez-Agirre, A.: SemEval-2012 task 6: a pilot on semantic textual similarity. In: *SEM 2012 - 1st Joint Conference on Lexical and Computational Semantics, pp. 385–393. Association for Computational Linguistics, Montréal, Canada (2012)
Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: AAAI 2016, pp. 2786–2792. AAAI Press, Phoenix, Arizona (2016)
Ranasinghe, T., Orasan, C., Mitkov, R.: Semantic textual similarity with siamese neural networks. In: RANLP 2019, Varna, Bulgaria (2019)
Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a “Siamese” time delay neural network. In: NIPS 1993 Proceedings of the 6th International Conference on Neural Information Processing Systems, pp. 737–744. Morgan Kaufmann Publishers Inc., Denver, Colorado (1993)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), pp. 539–546. IEEE, San Diego, CA, USA (2005)
Neculoiu, P., Versteegh, M., Rotaru, M.: Learning text similarity with siamese recurrent networks. In: Proceedings of the 1st Workshop on Representation Learning for NLP, pp. 148–157. Association for Computational Linguistics, Stroudsburg, PA, USA (2016)
Agirre, E., Cer, D., Diab, M., Gonzalez-Agirre, A., Guo, W.: ∗SEM 2013 shared task: semantic textual similarity. In: *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, pp. 32–43. Association for Computational Linguistics, Atlanta, Georgia, USA (2013)
Agirre, E., et al.: SemEval-2014 task 10: multilingual semantic textual similarity. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 81–91. Association for Computational Linguistics, Dublin, Ireland (2014)
Agirre, E., et al.: SemEval-2015 task 2: semantic textual similarity, English, Spanish and pilot on interpretability. In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pp. 252–263. Association for Computational Linguistics, Denver, Colorado (2015)
Agirre, E., et al.: SemEval-2016 task 1: semantic textual similarity, monolingual and cross-lingual evaluation. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 497–511. Association for Computational Linguistics, San Diego, California (2016)
Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., Specia, L.: SemEval-2017 task 1: semantic textual similarity multilingual and crosslingual focused evaluation. In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pp. 1–14. Association for Computational Linguistics, Vancouver, Canada (2017)
Bentivogli, L., Bernardi, R., Marelli, M., Menini, S., Baroni, M., Zamparelli, R.: SICK through the SemEval glasses. Lang. Resour. Eval. 50, 95–124 (2016). https://doi.org/10.1007/s10579-015-9332-5
Fonseca, E.R., dos Santos, L.B., Criscuolo, M.: Visão Geral da Avaliação de Similaridade Semântica e Inferência Textual. In: Linguamática, pp. 3–13 (2016)
Hartmann, N.S.: Solo queue at ASSIN: Combinando abordagens tradicionais e emergentes. Linguamatica. 8, 59–64 (2016)
Barbosa, L., Cavalin, P., Guimarães, V., Kormaksson, M.: Blue man group at ASSIN: using distributed representations for semantic similarity and entailment recognition. Linguamática. 8, 15–22 (2016)
Barrow, J., Peskov, D.: UMDeep at SemEval-2017 Task 1: end-to-end shared weight LSTM model for semantic textual similarity. In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pp. 180–184. Association for Computational Linguistics, Stroudsburg, PA, USA (2017)
Alves, A., Oliveira, H.G., Rodrigues, R., Encarnação, R.: ASAPP 2.0: advancing the state-of-the-art of semantic textual similarity for Portuguese. OpenAccess Ser. Informatics. 62, 1–12 (2018). https://doi.org/10.4230/OASIcs.SLATE.2018.12
Hartmann, N.S., Fonseca, E., Shulby, C.D., Treviso, M.V, Rodrigues, J.S., Aluísio, S.M.: Portuguese word embeddings: evaluating on word analogies and natural language tasks. In: Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology, pp. 122–131. Sociedade Brasileira de Computação, Uberlândia, MG, Brazil (2017)
e Oliveira, L.E.S., et al.: Learning Portuguese clinical word embeddings: a multi-specialty and multi-institutional corpus of clinical narratives supporting a downstream biomedical task. Stud. Health Technol. Inform. 264, 123–127 (2019). https://doi.org/10.3233/SHTI190196
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
de Souza, J.V.A., Oliveira, L.E.S.E., Gumiel, Y.B., Carvalho, D.R., Moro, C.M.C. (2020). Exploiting Siamese Neural Networks on Short Text Similarity Tasks for Multiple Domains and Languages. In: Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., Gonçalves, T. (eds) Computational Processing of the Portuguese Language. PROPOR 2020. Lecture Notes in Computer Science(), vol 12037. Springer, Cham. https://doi.org/10.1007/978-3-030-41505-1_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-41505-1_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41504-4
Online ISBN: 978-3-030-41505-1
eBook Packages: Computer ScienceComputer Science (R0)