Practice in Synonym Extraction at Large Scale

Synonym extraction is an important task in natural language processing and often used as a submodule in query expansion, question answering and other applications. Automatic synonym extractor is highly preferred for large scale applications. Previous studies in synonym extraction are most limited to small scale datasets. In this paper, we build a large dataset with 3.4 million synonym/nonsynonym pairs to capture the challenges in real world scenarios. We proposed (1) a new cost function to accommodate the unbalanced learning problem, and (2) a feature learning based deep neural network to model the complicated relationships in synonym pairs. We compare several different approaches based on SVMs and neural networks, and find out a novel feature learning based neural network outperforms the methods with hand-assigned features. Specifically, the best performance of our model surpasses the SVM baseline with a significant 97% relative improvement.