We propose a new neural model for word embeddings, which uses Unitary Matrices as the
primary device for encoding lexical information. It uses simple matrix multiplication to derive …

Transformer models perform well on NLP tasks, but recent theoretical studies suggest their
ability in modeling certain regular and context-free languages are limited. This creates a …

The emergence of powerful deep learning systems has largely displaced classical symbolic
algebraic models of linguistic representation in computational linguistics. While deep neural …

We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can
achieve encouraging accuracy on two types of syntactic patterns: context-free long distance …

Algebraic Structures in Natural Language Page 1 Page 2 Algebraic Structures in Natural
Language Algebraic Structures in Natural Language addresses a central problem in cognitive …

In this thesis, we studied whether self-attention networks can learn compositional seman-tics
using an arithmetic language. The goal of language aims to evaluate the meaning of nested …