# An Unsupervised Character-Aware Neural Approach to Word and Context Representation Learning

## TL;DR

This paper introduces an unsupervised neural model that learns word and context embeddings from characters, capturing morphological regularities and performing well on downstream tasks without fixed vocabularies.

## Contribution

It presents a novel character-aware neural architecture for unsupervised word and context embedding learning, reducing vocabulary constraints and improving performance.

## Key findings

- Model effectively captures morphological regularities.
- Achieves high performance with fewer parameters.
- Outperforms related state-of-the-art approaches.

## Abstract

In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, also known as "embeddings", are learned from unsupervised large corpora, they can be transferred to different tasks with positive effects in terms of performances, especially when only a few supervisions are available. In this work, we further extend this concept, and we present an unsupervised neural architecture that jointly learns word and context embeddings, processing words as sequences of characters. This allows our model to spot the regularities that are due to the word morphology, and to avoid the need of a fixed-sized input vocabulary of words. We show that we can learn compact encoders that, despite the relatively small number of parameters, reach high-level performances in downstream tasks, comparing them with related state-of-the-art approaches or with fully supervised methods.