Neural induction of a lexicon for fast and interpretable stance classification.

Clos, J�r�mie; Wiratunga, Nirmalie

Abstract

Large-scale social media classification faces the following two challenges: algorithms can be hard to adapt to Web-scale data, and the predictions that they provide are difficult for humans to understand. Those two challenges are solved at the cost of some accuracy by lexicon-based classifiers, which offer a white-box approach to text mining by using a trivially interpretable additive model. However current techniques for lexicon-based classification limit themselves to using hand-crafted lexicons, which suffer from human bias and are difficult to extend, or automatically generated lexicons, which are induced using point-estimates of some predefined probabilistic measure on a corpus of interest. In this work we propose a new approach to learn robust lexicons, using the backpropagation algorithm to ensure generalization power without sacrificing model readability. We evaluate our approach on a stance detection task, on two different datasets, and find that our lexicon outperforms standard lexicon approaches.

Citation

CLOS, J. and WIRATUNGA, N. 2017. Neural induction of a lexicon for fast and interpretable stance classification. In Gracia, J., Bond, F., McCrae, J.P., Buitelaar, P., Chiarcos, C. and Hellmann, S. (eds.) Language, data and knowledge: proceedings of the 1st International conference on language, data and knowledge (LDK 2017), 19-20 June 2017, Galway, Ireland. Lecture notes in computer science, 10318. Cham: Springer [online], pages 181-193. Available from: https://doi.org/10.1007/978-3-319-59888-8_16

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 1st International conference on language, data and knowledge (LDK 2017)
• Start Date: Jun 19, 2017
• End Date: Jun 20, 2017
• Acceptance Date: Apr 4, 2017
• Online Publication Date: May 27, 2017
• Publication Date: May 27, 2017
• Deposit Date: Jun 4, 2018
• Publicly Available Date: Jun 4, 2018
• Print ISSN: 0302-9743
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 181-193
• Series Title: Lecture notes in computer science
• Series Number: 10318
• Series ISSN: 0302-9743
• ISBN: 9783319598871
• DOI: https://doi.org/10.1007/978-3-319-59888-8_16
• Keywords: Decision function; Aggregation function; Computational graph; Sentiment lexicon; Pointwise mutual information
• Public URL: http://hdl.handle.net/10059/2940
• Contract Date: Jun 4, 2018