Work

Learning and analyzing vector encoding of symbolic representations

Year: 2018

Type: preprint

Abstract: We present a formal language with expressions denoting general symbol structures and queries which access information in those structures. A sequence-to-sequence network processing this language learns to encode symbol structures and query them. The learned representation (approximately) shares a simple linearity property with theoretical techniques for performing this task.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1803.03834

Authors: Fernandez, Roland, Celikyilmaz, Asli, Singh, Rishabh, Smolensky, Paul

Institutions: Microsoft (United States), Google (United States)

Language: English

Topic: semigroups and automata theory

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2793170671

Cites: 12

Cited by: 2

Related to: 20