Featureless Domain-Specific Term Extraction with Minimal Labelled Data

Supervised domain-specific term extraction often suffers from two common problems, namely labourious manual feature selection, and the lack of labelled data. In this paper, we introduce a weakly supervised bootstrapping approach using two deep learning classifiers. Each classifier learns the representations of terms separately by taking word embedding vectors as inputs, thus no manually selected feature is required. The two classifiers are firstly trained on a small set of labelled data, then independently make predictions on a subset of the unlabeled data. The most confident predictions are subsequently added to the training set to retrain the classifiers. This co-training process minimises the reliance on labelled data. Evaluations on two datasets demonstrate that the proposed co-training approach achieves a competitive performance with limited training data as compared to standard supervised learning baseline.