CLFeb 2, 2017

Symbolic, Distributed and Distributional Representations for Natural Language Processing in the Era of Deep Learning: a Survey

arXiv:1702.00764v242 citations
AI Analysis

It addresses the foundational problem of understanding how discrete symbols are represented in neural networks for the NLP community, but it is incremental as a survey.

The paper surveys the relationship between symbolic representations and distributed/distributional representations in NLP, aiming to renew this link to inspire new deep learning networks.

Natural language is inherently a discrete symbolic representation of human knowledge. Recent advances in machine learning (ML) and in natural language processing (NLP) seem to contradict the above intuition: discrete symbols are fading away, erased by vectors or tensors called distributed and distributional representations. However, there is a strict link between distributed/distributional representations and discrete symbols, being the first an approximation of the second. A clearer understanding of the strict link between distributed/distributional representations and symbols may certainly lead to radically new deep learning networks. In this paper we make a survey that aims to renew the link between symbolic representations and distributed/distributional representations. This is the right time to revitalize the area of interpreting how discrete symbols are represented inside neural networks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes