Neural ParsCit: A Deep Learning Based Reference String Parser

We present a deep learning approach for the core digital libraries task of parsing bibliographic reference strings. We deploy the state-of-the-art Long Short-Term Memory (LSTM) neural network architecture, a variant of a recurrent neural network (RNN) to capture long-range dependencies in reference strings. We explore word embeddings and character-based word embeddings as an alternative to handcrafted features. We incrementally experiment with features, architectural configurations, and diversity of the dataset. Our final proposed model is an LSTM-based architecture, which uses a linear-chain Conditional Random Field (CRF) layer over the LSTM output. In extensive experiments in both English in-domain (computer science) and out-of-domain (humanities) test cases, as well as multilingual data, our results show a significant gain (p < 0.01) over the reported stateof-the-art CRF-only based parser.