ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers

Bibliographic reference parsers extract machine-readable metadata such as author names, title, journal, and year from bibliographic reference strings. To extract the metadata, the parsers apply heuristics or machine learning. However, no reference parser, and no algorithm, consistently gives the best results in every scenario. For instance, one tool may be best in extracting titles in ACM citation style, but only third best when APA is used. Another tool may be best in extracting English author names, while another one is best for noisy data (i.e. inconsistent citation styles). In this paper, which is an extended version of our recent RecSys poster, we address the problem of reference parsing from a recommender-systems and meta-learning perspective. We propose ParsRec, a meta-learning based recommender-system that recommends the potentially most effective parser for a given reference string. ParsRec recommends one out of 10 open-source parsers: Anystyle-Parser, Biblio, CERMINE, Citation, Citation-Parser, GROBID, ParsCit, PDFSSA4MET, Reference Tagger, and Science Parse. We evaluate ParsRec on 105k references from chemistry. We propose two approaches to meta-learning recommendations. The first approach learns the best parser for an entire reference string. The second approach learns the best parser for each metadata type in a reference string. The second approach achieved a 2.6% increase in F1 (0.909 vs. 0.886) over the best single parser (GROBID), reducing the false positive rate by 20.2% (0.075 vs. 0.094), and the false negative rate by 18.9% (0.107 vs. 0.132).

[1]  Jöran Beel,et al.  Machine Learning vs. Rules and Out-of-the-Box vs. Retrained: An Evaluation of Open-Source Bibliographic Reference and Citation Parsers , 2018, JCDL.

[2]  Jöran Beel,et al.  Mr. DLib: Recommendations-as-a-Service (RaaS) for Academia , 2017, 2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL).

[3]  James P. Callan,et al.  Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding , 2017, WWW.

[4]  Robin D. Burke,et al.  Hybrid Web Recommender Systems , 2007, The Adaptive Web.

[5]  Asif Ekbal,et al.  Simulated annealing based classifier ensemble techniques: Application to part of speech tagging , 2013, Inf. Fusion.

[6]  Jan-Ming Ho,et al.  BibPro: A Citation Parser Based on Sequence Alignment , 2012, IEEE Trans. Knowl. Data Eng..

[7]  Patrice Lopez,et al.  GROBID: Combining Automatic Bibliographic Data Recognition and Term Extraction for Scholarship Publications , 2009, ECDL.

[8]  Min-Yen Kan,et al.  Scholarly Document Information Extraction using Extensible Features for Efficient Higher Order Semi-CRFs , 2015, JCDL.

[9]  Dominika Tkaczyk,et al.  Large scale citation matching using Apache Hadoop , 2013, TPDL.

[10]  Bogdan Gabrys,et al.  Metalearning: a survey of trends and technologies , 2013, Artificial Intelligence Review.

[11]  Francesco Ricci,et al.  Switching hybrid for cold-starting context-aware recommender systems , 2014, RecSys '14.

[12]  C. Lee Giles,et al.  ParsCit: an Open-source CRF Reference String Parsing Package , 2008, LREC.

[13]  Roman Kern,et al.  TeamBeam - Meta-Data Extraction from Scientific Literature , 2012, D Lib Mag..

[14]  Per Ahlgren,et al.  Document-document similarity approaches and science mapping: Experimental comparison of five approaches , 2009, J. Informetrics.

[15]  Hannah Bast,et al.  The Icecite Research Paper Management System , 2013, WISE.

[16]  Ying Su,et al.  Ensemble Learning for Sentiment Classification , 2012, CLSW.

[17]  Dominika Tkaczyk,et al.  CERMINE: automatic extraction of structured metadata from scientific literature , 2015, International Journal on Document Analysis and Recognition (IJDAR).

[18]  Jorge E. Hirsch,et al.  An index to quantify an individual’s scientific research output that takes into account the effect of multiple coauthorship , 2009, Scientometrics.

[19]  Andrei Voronkov,et al.  PDFX: fully-automated PDF-to-XML conversion of scientific literature , 2013, ACM Symposium on Document Engineering.

[20]  Vicente P. Guerrero-Bote,et al.  A new approach to the metric of journals' scientific prestige: The SJR indicator , 2010, J. Informetrics.

[21]  Bela Gipp,et al.  Research-paper recommender systems: a literature survey , 2015, International Journal on Digital Libraries.

[22]  Manpreet Kaur,et al.  Neural ParsCit: a deep learning-based reference string parser , 2018, International Journal on Digital Libraries.

[23]  Wolfgang Glänzel,et al.  A Hirsch-type index for journals , 2006, Scientometrics.

[24]  Jöran Beel,et al.  ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing , 2018, ArXiv.

[25]  Francisco Herrera,et al.  A methodology for Institution-Field ranking based on a bidimensional analysis: the IFQ2A index , 2011, Scientometrics.

[26]  Fatemeh Vahedian,et al.  Weighted hybrid recommendation for heterogeneous networks , 2014, RecSys '14.

[27]  Dominika Tkaczyk,et al.  Extracting Contextual Information from Scientific Literature Using CERMINE System , 2015, SemWebEval@ESWC.

[28]  Gary Geunbae Lee,et al.  A Meta Learning Approach to Grammatical Error Correction , 2012, ACL.

[29]  Cornelia Caragea,et al.  CiteSeerX: AI in a Digital Library Search Engine , 2014, AI Mag..