Identifying problems and solutions in scientific text.
Publication Date
2018-01Journal Title
Scientometrics
ISSN
0138-9130
Publisher
Akademiai Kiado
Volume
116
Issue
2
Pages
1367-1382
Language
eng
Type
Article
This Version
VoR
Physical Medium
Print-Electronic
Metadata
Show full item recordCitation
Heffernan, K., & Teufel, S. (2018). Identifying problems and solutions in scientific text.. Scientometrics, 116 (2), 1367-1382. https://doi.org/10.1007/s11192-018-2718-6
Abstract
Research is often described as a problem-solving activity, and as
a result, descriptions of problems and solutions are an essential part of the
scienti c discourse used to describe research activity. We present an automatic
classi er that, given a phrase that may or may not be a description of a
scienti c problem or a solution, makes a binary decision about problemhood
and solutionhood of that phrase. We recast the problem as a supervised machine
learning problem, de ne a set of 15 features correlated with the target
categories and use several machine learning algorithms on this task. We also
create our own corpus of 2000 positive and negative examples of problems and
solutions. We nd that we can distinguish problems from non-problems with
an accuracy of 82.3%, and solutions from non-solutions with an accuracy of
79.7%. Our three most helpful features for the task are syntactic information
(POS tags), document and word embeddings.
Sponsorship
EPSRC (1641528)
Embargo Lift Date
2100-01-01
Identifiers
External DOI: https://doi.org/10.1007/s11192-018-2718-6
This record's URL: https://www.repository.cam.ac.uk/handle/1810/276671
Recommended or similar items
The following licence files are associated with this item: