doi.bio/cicero_dos_santos

Cicero Nogueira dos Santos

Early Life and Education

Cicero Nogueira dos Santos is a Brazilian researcher with a focus on machine learning applied to natural language processing. He received his PhD in Computational Linguistics from the University of São Paulo in 2009, where he also completed his postdoctoral studies.

Career and Research

Dos Santos is currently a research scientist at Google, working on machine learning and natural language processing. He previously held positions at Amazon Web Services and IBM Research, where he focused on AI foundations, neural networks, and semi-supervised learning.

Dos Santos has published extensively in the field of natural language processing, with a particular interest in large language models (LLMs) and their applications. Some of his notable works include:

• "Learning Implicit Text Generation via Feature Matching"
• "Learning Implicit Generative Models by Matching Perceptual Features"
• "End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems"
• "Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks"
• "LSTM-based Deep Learning Models for Non-factoid Answer Selection"
• "Boosting Named Entity Recognition with Neural Character Embeddings"
• "Think Positive: Towards Twitter Sentiment Analysis from Scratch"

He has also received several awards for his research, including the IBM Research Division Award and first place at the 16th Conference on Computational Natural Language Learning for his work on coreference resolution.

Selected Bibliography

• Dos Santos, C. N. (2014). Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks.
• Dos Santos, C. N., & Rezende Fernandes, E. (2014). Latent Trees for Coreference Resolution. Computational Linguistics, 40(2), 361-385.
• Dos Santos, C. N. (2014). Think Positive: Towards Twitter Sentiment Analysis from Scratch. Proceedings of the International Workshop on Semantic Evaluation, 1-7.
• Dos Santos, C. N., & de Bayser, M. G. (2014). Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts. Proceedings of the International Conference on Computational Linguistics, 237-246.
• Dos Santos, C. N. (2016). Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond. Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, 23-28.