+ speed (tests run 5 times faster, including Travis)
+ more readability
+ more control
+ more stable (damn mvn plugins!)
- but no war generated for Tomcat/JBoss deployment
(issue #272)
Ratcliff/Obershelp Matching =
(Minimum Ratcliff/Obershelp similarity at 0.95)
all fields 98.69 88.45 77.69 82.72 (micro average)
98.69 88.03 77.8 82.57 (macro average)
all fields 98.58 89.83 80.1 84.68 (micro average)
98.58 89.85 80.27 84.77 (macro average)
Test with 3,185 documents 64,495 references in total, mostly from chemical domains
D Tkaczyk, A Collins, P Sheridan, J Beel - arXiv preprint arXiv:1802.01168, 2018 - arxiv.org
(author of CERMINE)
Ratcliff/Obershelp Matching, similarity at 0.95)
===== Field-level results ===== end 2015
label accuracy precision recall f1
all fields 95.2 78.03 71.45 74.59 (micro average)
95.2 77.98 70.86 74.17 (macro average)
===== Field-level results ===== version 0.4.1
all fields 95.69 80.31 74.71 77.41 (micro average)
95.69 80.57 74.32 77.24 (macro average)
===== Field-level results ===== with current with new CrossRef API - v0.5.1
all fields 96.56 87.39 82.98 85.13 (micro average)
96.56 86.94 82.08 84.32 (macro average)
Better PDF parsing: pdfalto (composed and special characters, reading order, spacing, etc.)
Structuring ebook (pdf/ALTO): training based on embedded "outline" (project Opaline)
Long due new header model: regenerate and reformat training data, new features, etc. targeting 0.90 f1 instance-based
New DL models for sequence labelling, and for text classification (Keras, efficient java embeddings)
it is challenging to make it production ready (loading of resources, native integration, memory usage)