Analyzing Structures in the Semantic Vector Space: A Framework for Decomposing Word Embeddings

TL;DR

This paper introduces a framework for decomposing word embeddings into sub-vectors to better understand their semantic structure and improve NLP tasks like category completion and word analogy solving.

Contribution

The paper presents a novel framework for decomposing word embeddings into meaningful sub-vectors, enhancing interpretability and task performance.

Findings

Sub-vector approach outperforms supervised methods in category completion.

Sub-vector method significantly improves word analogy task accuracy.

Framework enables detailed analysis of semantic encoding in embeddings.

Abstract

Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks. However, word embeddings are represented by dense, real-valued vectors and they are therefore not directly interpretable. Thus, computational operations based on them are also not well understood. In this paper, we present an approach for analyzing structures in the semantic vector space to get a better understanding of the underlying semantic encoding principles. We present a framework for decomposing word embeddings into smaller meaningful units which we call sub-vectors. The framework opens up a wide range of possibilities analyzing phenomena in vector space semantics, as well as solving concrete NLP problems: We introduce the category completion task and show that a sub-vector based approach is superior to supervised techniques; We present a sub-vector based method for solving the word analogy task, which substantially outperforms different variants of the traditional vector-offset method.