Back to the future: logic and machine learning

Simon Dobnik, John D. Kelleher

Research output: Contribution to conferencePaperpeer-review

Abstract

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.
Original languageEnglish
DOIs
Publication statusPublished - 2017
EventLaML: Conference on Logic and Machine Learning in Natural Language - Gothenburg, Sweden
Duration: 12 Jun 201714 Jun 2017

Conference

ConferenceLaML: Conference on Logic and Machine Learning in Natural Language
Country/TerritorySweden
CityGothenburg
Period12/06/1714/06/17

Keywords

  • logic
  • machine learning
  • natural language processing
  • computational linguistics
  • top-down approaches
  • data-driven approaches
  • deep learning
  • language technology

Fingerprint

Dive into the research topics of 'Back to the future: logic and machine learning'. Together they form a unique fingerprint.

Cite this