Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
1. NATURAL SCIENCES, 1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences
In this paper we argue that since the beginning of the natural language processing or computational linguistics there has been a strong connection between logic and machine learning. First of all, there is something logical about language or linguistic about logic. Secondly, we argue that rather than distinguishing between logic and machine learning, a more useful distinction is between top-down approaches and data-driven approaches. Examining some recent approaches in deep learning we argue that they incorporate both properties and this is the reason for their very successful adoption to solve several problems within language technology.
Dobnik, S. & Kelleher, J. (2017). Back to the future: logic and machine learning. LaML:Conference on Logic and Machine Learning in Natural Language , Gothenburg, Sweden, 12th-14th June, 2017. doi:10.21427/D7041Z
ADAPT Research Centre
Paper presented at the Conference on Logic and Machine Learning in Natural Language (LaML), Gothenburg, Sweden, 12th-14th June, 2017. The conference was organised and hosted by the Centre for Linguistic Theory and Studies in Probability (CLASP) at the University of Gothenburg. Conference website: http://clasp.gu.se/news-events/conference-on-logic-and-machine-learning-in-natural-language--laml-