%0 Journal Article %1 prasad2018neural %A Prasad, Animesh %A Kaur, Manpreet %A Kan, Min-Yen %D 2018 %J International Journal on Digital Libraries %K citation deep deeplearning extraction learning lstm network neural %N 4 %P 323--337 %R 10.1007/s00799-018-0242-1 %T Neural ParsCit: a deep learning-based reference string parser %U https://doi.org/10.1007/s00799-018-0242-1 %V 19 %X 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 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 the diversity of the dataset. Our final model is an LSTM-based architecture, which layers a linear chain conditional random field (CRF) 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 state-of-the-art CRF-only-based parser.

@article{prasad2018neural, abstract = {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 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 the diversity of the dataset. Our final model is an LSTM-based architecture, which layers a linear chain conditional random field (CRF) 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 state-of-the-art CRF-only-based parser.}, added-at = {2021-03-11T10:40:31.000+0100}, author = {Prasad, Animesh and Kaur, Manpreet and Kan, Min-Yen}, biburl = {https://www.bibsonomy.org/bibtex/212216ebb520d67e99deeb8c8176c46f5/jaeschke}, day = 01, description = {Neural ParsCit: a deep learning-based reference string parser | SpringerLink}, doi = {10.1007/s00799-018-0242-1}, interhash = {92518150147cfece10d625d292697166}, intrahash = {12216ebb520d67e99deeb8c8176c46f5}, issn = {1432-1300}, journal = {International Journal on Digital Libraries}, keywords = {citation deep deeplearning extraction learning lstm network neural}, month = nov, number = 4, pages = {323--337}, timestamp = {2021-05-19T08:35:34.000+0200}, title = {Neural ParsCit: a deep learning-based reference string parser}, url = {https://doi.org/10.1007/s00799-018-0242-1}, volume = 19, year = 2018 }