Natural Language Understanding and Prediction: from Formal Grammars to Large Scale Machine Learning

Issue title: Formal Models - Computability, Complexity, Applications

Article type: Research Article

Authors: Duta, Nicolae

Affiliations: New England Research and Development Center, Microsoft, Cambridge, USA. niduta@microsoft.com

Note: [] Address for correspondence: Microsoft NERD Center, One Memorial Drive, Cambridge, MA, 02142, USA

Abstract: Scientists have long dreamed of creating machines humans could interact with by voice. Although one no longer believes Turing's prophecy that machines will be able to converse like humans in the near future, real progress has been made in the voice and text-based human-machine interaction. This paper is a light introduction and survey of some deployed natural language systems and technologies and their historical evolution. We review two fundamental problems involving natural language: the language prediction problem and the language understanding problem. While describing in detail all these technologies is beyond our scope, we do comment on some aspects less discussed in the literature such as language prediction using huge models and semantic labeling using Marcus contextual grammars.

Keywords: Natural language understanding, language modeling, language prediction

DOI: 10.3233/FI-2014-1023

Journal: Fundamenta Informaticae, vol. 131, no. 3-4, pp. 425-440, 2014