Juan Manuel Pérez
PhD Student and TA at Facultad de Ciencias Exactas, Universidad de Buenos Aires
My name is Juan Manuel, I’m a PhD student and a TA at Departamento de Computación, FCEyN, Universidad de Buenos Aires
I study Natural Language Processing, and my main area of interest is the detection of Hate Speech and Abusive Language in Social Media. I’m also fond of sociolinguistics in social media.
Email: my university email (jmperez at dc uba ar) may not work properly – contact me at yo at jmperez dot com dot ar
[github] – [linkedin] – [twitter]
Publications
- Juan Manuel Pérez, Damián E. Aleman “Exploiting user-frequency information for mining regionalisms from Social Media texts” JM Pérez, DE Aleman, SN Kalinowski, A Gravano. arXiv preprint arXiv:1907.04492
- Pérez Juan Manuel, Luque Franco “Atalaya at SemEval 2019 Task 5: Robust Embeddings for Tweet Classification.”. Proceedings of the 13th International Workshop on Semantic Evaluation. 2019.
- Cotik, Viviana; Pérez Juan Manuel, Luque Franco “Window Classifiers and Conditional Random Fields for Medical Report De-Identification”. Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2019).
- Luque, Franco M., Pérez, Juan Manuel “Atalaya at TASS 2018: Sentiment analysis with tweet embeddings and data augmentation” Proceedings of TASS 2018: Workshop on Semantic Analysis at SEPLN (TASS 2018). Vol. 2172. 2018.
- Pablo Brusco, Juan Manuel Pérez, Agustín Gravano “Cross-linguistic study of the production of turn-taking cues in American English and Argentine Spanish”. Interspeech (2017)
- Janine Kleinhans, Mireia Farrús, Agustín Gravano, Juan Manuel Pérez, Catherine Lai, Leo Wanner “Using Prosody to Classify Discourse Relations”, Interspeech (2017)
- Juan Manuel Pérez, Ramiro H. Gálvez, and Agustın Gravano. “Disentrainment may be a positive thing: A novel measure of unsigned acoustic-prosodic synchrony, and its relation to speaker engagement.” Interspeech 2016 (2016): 1270-1274.
Resources
RoBERTuito: A pre-trained model for social media text
pysentimiento: A multilingual toolkit for Sentiment Analysis and other Social NLP tasks
“Herramientas computacionales para entender el español de Argentina en Twitter”
Workshop given at Universidad de Córdoba, in the context of the “VIII Congreso Internacional de la Lengua Española”
CV
You can download my CV here