Detección de Sarcasmo con BERT

• Autores: Elsa Scola, Isabel Segura Bedmar
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 67, 2021, págs. 13-25
• Idioma: inglés
• Títulos paralelos:
  • Sarcasm Detection with BERT
• Enlaces
  • Texto completo
• Resumen
  • español

    El sarcasmo se usa con frecuencia para realizar crítica o burla indirecta, a veces hiriendo los sentimientos de alguien. Algunas veces, las personas tienen dificultades para reconocer los comentarios sarcásticos, ya que decimos lo contrario de lo que realmente queremos decir. Por lo tanto, la detección automática de sarcasmo en textos es una de las tareas más complicadas en el Procesamiento del Lenguaje Natural (PLN). Además, se ha convertido en un área de investigación relevante debido a su importancia para mejorar el análisis de sentimientos. En este trabajo, exploramos varios modelos de aprendizaje profundo, como Bidirectional Long Short-Term Memory (BiLSTM) y Bidirectional Encoder Representations fromTransformers (BERT) para abordar la tarea de detección de sarcasmo. Si bien la mayoría de los trabajos anteriores se han centrado en datasets construidos con textos de redes sociales, en este artículo, evaluamos nuestros modelos utilizando un dataset formado por titulares de noticias. Por tanto, este es el primer estudio que aplica BERT para detectar el sarcasmo en textos que no provienen de las redes sociales. Los resultados de los experimentos muestran que el enfoque basado en BERT supera el estado del arte en este tipo de conjunto de datos.

  • English

    Sarcasm is often used to humorously criticize something or hurt someone’s feelings. Humans often have difficulty in recognizing sarcastic comments since we say the opposite of what we really mean. Thus, automatic sarcasm detection in textual data is one of the most challenging tasks in Natural Language Processing (NLP). It has also become a relevant research area due to its importance in the improvement of sentiment analysis. In this work, we explore several deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Encoder Representations from Transformers (BERT) to address the task of sarcasm detection. While most research has been conducted using social media data, we evaluate our models using a news headlines dataset. To the best of our knowledge, this is the first study that applies BERT to detect sarcasm in texts that do not come from social media. Experiment results show that the BERT-based approach overcomes the state-of-the-art on this type of dataset.

• Referencias bibliográficas
  • Amir, S., B. C. Wallace, H. Lyu, P. Carvalho, and M. J. Silva. 2016. Modelling conElsa Scola, Isabel Segura-Bedmar 22 text with user embeddings...
  • Apidianaki, M., S. M. Mohammad, J. May, E. Shutova, S. Bethard, and M. Carpuat, editors. 2018. Proceedings of The 12th International Workshop...
  • Bamman, D. and N. A. Smith. 2015. Contextualized sarcasm detection on twitter. In Proceedins of the 9TH International AAAI Conference On Web...
  • Cai, Y., H. Cai, and X. Wan. 2019. Multimodal sarcasm detection in twitter with hierarchical fusion model. In Proceedings of the 57th Annual...
  • Capelli, C. A., N. Nakagawa, and C. M. Madden. 1990. How children understand sarcasm: The role of context and intonation. Child Development,...
  • Castro, S., D. Hazarika, V. P´erez-Rosas, R. Zimmermann, R. Mihalcea, and S. Poria. 2019. Towards multimodal sarcasm detection (an Obviously...
  • Cortes, C. and V. Vapnik. 1995. Supportvector networks. Machine learning, 20(3):273–297.
  • Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding....
  • Eke, C. I., A. A. Norman, L. Shuib, and H. F. Nweke. 2020. Sarcasm identification in textual data: systematic review, research challenges...
  • Garain, A. 2019. Humor analysis based on human annotation(haha)-2019: Humor analysis at tweet level using deep learning. In Proceedings of...
  • Garain, A. and S. K. Mahata. 2019. Sentiment analysis at SEPLN (TASS)-2019: sentiment analysis at tweet level using deep learning. In Proceedings...
  • Ghosh, A. and T. Veale. 2016. Fracking sarcasm using neural network. In Proceedings of the 7th Workshop on Computational Approaches to Subjectivity,...
  • Ghosh, D., A. Richard Fabbri, and S. Muresan. 2017. The role of conversation context for sarcasm detection in online interactions. In Proceedings...
  • Hakala, K. and S. Pyysalo. 2019. Biomedical named entity recognition with multilingual BERT. In Proceedings of The 5th Workshop on BioNLP...
  • Hernandez Farias, D., V. Patti, and P. Rosso. 2016. Irony detection in twitter: The role of affective content. ACM Transactions on Internet...
  • Hochreiter, S. and J. Schmidhuber. 1997. Long short-term memory. Neural computation, 9:1735–80, 12.
  • Joshi, A., P. Bhattacharyya, M. Carman, J. Saraswati, and R. Shukla. 2016. How do cultural differences impact the quality of sarcasm annotation?:...
  • Joulin, A., E. Grave, P. Bojanowski, M. Douze, H. J´egou, and T. Mikolov. 2017. Fasttext. zip: Compressing text classification models. In...
  • Khatri, A. and P. P. 2020. Sarcasm detection in tweets with bert and glove embeddings. In Proceedings of the Second Workshop on Figurative...
  • Khodak, M., N. Saunshi, and K. Vodrahalli. 2018. A large self-annotated corpus for sarcasm. In Proceedings of the 11th International Conference...
  • Kim, Y. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural...
  • Kingma, D. P. and J. Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR...
  • Lee, J., W. Yoon, S. Kim, D. Kim, S. Kim, C. H. So, and J. Kang. 2020. Biobert: a pre-trained biomedical language representation model for...
  • Liebrecht, C., F. Kunneman, and A. van den Bosch. 2013. The perfect solution for detecting sarcasm in tweets #not. In Proceedings of the 4th...
  • Littlestone, N. 1988. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2(4):285–318.
  • Mikolov, T., I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. 2013. Distributed representations of words and phrases and their compositionality....
  • Misra, R. and P. Arora. 2019. Sarcasm detection using hybrid neural network. arXiv preprint arXiv:1908.07414.
  • Nigam, K. 1999. Using maximum entropy for text classification. In Proceedings of IJCAI-99 Workshop on Machine Learning for Information Filtering,...
  • Oprea, S. and W. Magdy. 2020. iSarcasm: A dataset of intended sarcasm. In Proceedings of the 58th Annual Meeting of the Association for Computational...
  • Oraby, S., V. Harrison, L. Reed, E. Hernandez, E. Riloff, and M. Walker. 2016a. Creating and characterizing a diverse corpus of sarcasm in...
  • Oraby, S., V. Harrison, L. Reed, E. Hernandez, E. Riloff, and M. A. Walker. 2016b. Creating and characterizing a diverse corpus of sarcasm...
  • Ortega-Bueno, R., F. Rangel, D. Hern´andez Farıas, P. Rosso, M. Montes-y G´omez, and J. E. Medina Pagola. 2019. Overview of the task on irony...
  • Pennington, J., R. Socher, and C. D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on...
  • Pt´aˇcek, T., I. Habernal, and J. Hong. 2014. Sarcasm detection on Czech and English Twitter. In Proceedings of COLING 2014, the 25th International...
  • Riloff, E., A. Qadir, P. Surve, L. De Silva, N. Gilbert, and R. Huang. 2013. Sarcasm as contrast between a positive senElsa Scola, Isabel...
  • Rockwell, P. and E. M. Theriot. 2001. Culture, gender, and gender mix in encoders of sarcasm: A self-assessment analysis. Communication Research...
  • Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from...
  • Wang, J.-H., T.-W. Liu, X. Luo, and L. Wang. 2018. An lstm approach to short text sentiment classification with word embeddings. In Proceedings...
  • Xu, L. and V. Xu. 2019. Project report: Sarcasm detection. https://web.stanford.edu/class/archive/ cs/cs224n/cs224n.1194/project.html. Online;...
  • Zheng, S. and M. Yang. 2019. A new method of improving bert for text classification. In Proceedings of International Conference on Intelligent...
  • Zhou, P., Z. Qi, S. Zheng, J. Xu, H. Bao, and B. Xu. 2016. Text classification improved by integrating bidirectional LSTM with two-dimensional...