@inproceedings{ccbe7c83777447c9a531012337a9e515,
title = "Selecting documents relevant for chemistry as a classification problem",
abstract = "We present a first version of a system for selecting chemical publications for inclusion in a chemistry information database. This database, Reaxys (https://www.elsevier.com/solutions/reaxys), is a portal for the retrieval of structured chemistry information from published journals and patents. There are three challenges in this task: (i) Training and input data are highly imbalanced; (ii) High recall (≥95%) is desired; and (iii) Data offered for selection is numerically massive but at the same time, incomplete. Our system successfully handles the imbalance with the undersampling technique and achieves relatively high recall using chemical named entities as features. Experiments on a real-world data set consisting of 15,822 documents show that the features of chemical named entities boost recall by 8% over the usual n-gram features being widely used in general document classification applications. For fostering research on this challenging topic, a part of the data set compiled in this paper can be requested.",
keywords = "Document classification, Language processing, Machine learning cheminfomatics, Natural",
author = "Zhemin Zhu and Akhondi, {Saber A.} and Umesh Nandal and Marius Doornenbal and Michelle Gregory",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 20th International Conference on Knowledge Engineering and Knowledge Management, EKAW 2016 ; Conference date: 19-11-2016 Through 23-11-2016",
year = "2017",
month = jan,
day = "1",
doi = "10.1007/978-3-319-58694-6_31",
language = "English",
isbn = "9783319586939",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "198--201",
editor = "Suarez-Figueroa, {Mari Carmen} and Jun Zhao and Matthew Horridge and Valentina Presutti and Tudor Groza and Mathieu d{\textquoteright}Aquin and Paolo Ciancarini and Francesco Poggi",
booktitle = "Knowledge Engineering and Knowledge Management - EKAW 2016 Satellite Events, EKM and Drift-an-LOD, Revised Selected Papers",
}