Yatian Shen


2016

pdf bib
Attention-Based Convolutional Neural Network for Semantic Relation Extraction
Yatian Shen | Xuanjing Huang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Nowadays, neural networks play an important role in the task of relation classification. In this paper, we propose a novel attention-based convolutional neural network architecture for this task. Our model makes full use of word embedding, part-of-speech tag embedding and position embedding information. Word level attention mechanism is able to better determine which parts of the sentence are most influential with respect to the two entities of interest. This architecture enables learning some important features from task-specific labeled data, forgoing the need for external knowledge such as explicit dependency structures. Experiments on the SemEval-2010 Task 8 benchmark dataset show that our model achieves better performances than several state-of-the-art neural network models and can achieve a competitive performance just with minimal feature engineering.

2014

pdf bib
Bilingual Product Name Dictionary Construction Using a Two Stage Method
Yatian Shen | Xuanjing Huang
Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing

Search
Co-authors
Venues