Practice in Synonym Extraction at Large Scale
This addresses the problem of scaling synonym extraction for NLP applications like query expansion, but it is incremental as it builds on existing methods with new data and optimizations.
The paper tackled synonym extraction at large scale by building a dataset of 3.4 million pairs and proposing a new cost function and deep neural network, resulting in a 97% relative improvement over an SVM baseline.
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/non-synonym 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.