arXiv Open Access 2018

Learning and analyzing vector encoding of symbolic representations

Roland Fernandez Asli Celikyilmaz Rishabh Singh Paul Smolensky

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.AI

Penulis (4)

Roland Fernandez

Asli Celikyilmaz

Rishabh Singh

Paul Smolensky

Format Sitasi

APA MLA BibTeX

Fernandez, R., Celikyilmaz, A., Singh, R., Smolensky, P. (2018). Learning and analyzing vector encoding of symbolic representations. https://arxiv.org/abs/1803.03834

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2018
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓