Cícero dos Santos

Improved Neural Relation Detection for Knowledge Base Question Answering

2017 · arXiv (Cornell University)

Relation detection is a core component for many NLP applications including Knowledge Base Question Answering (KBQA). In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning that detects KB relations given …

Classifying Relations by Ranking with Convolutional Neural Networks

2015 · arXiv (Cornell University)

Cícero dos Santos, Bing Xiang, Bowen Zhou. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

LSTM-based Deep Learning Models for Non-factoid Answer Selection

2015 · arXiv (Cornell University)

In this paper, we apply a general deep learning (DL) framework for the answer selection task, which does not depend on manually defined features or linguistic tools. The basic framework is to build the embeddings …

Learning Hybrid Representations to Retrieve Semantically Equivalent Questions

2015

Cícero dos Santos, Luciano Barbosa, Dasha Bogdanova, Bianca Zadrozny. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). …

Improved Representation Learning for Question Answer Matching

2016

Passage-level question answer matching is a challenging task since it requires effective representations that capture the complex semantic relations between questions and answers. In this work, we propose a series of deep learning models to …