ParsRec: Meta-Learning Recommendations for Bibliographic Reference Parsing
This work addresses the inconsistency in bibliographic reference parsing for researchers and librarians by providing a meta-learning recommendation system, though it is incremental as it builds on existing parsers.
The paper tackled the problem of bibliographic reference parsing by proposing ParsRec, a meta-learning approach that recommends the best parser(s) for each reference string, achieving a 2.6% increase in F1 score (0.909 vs. 0.886) and reducing false positive and false negative rates by over 18% compared to the best single parser.
Bibliographic reference parsers extract metadata (e.g. author names, title, year) from bibliographic reference strings. No reference parser consistently gives the best results in every scenario. For instance, one tool may be best in extracting titles, and another tool in extracting author names. In this paper, we address the problem of reference parsing from a recommender-systems perspective. We propose ParsRec, a meta-learning approach that recommends the potentially best parser(s) for a given reference string. 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 field of a reference string. The second approach achieved a 2.6% increase in F1 (0.909 vs. 0.886, p < 0.001) 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).