Learning Analogy-Preserving Sentence Embeddings for Answer Selection

TL;DR

This paper introduces a neural network framework for learning sentence embeddings that preserve analogical relations, improving answer selection by leveraging analogical inference rather than just semantic similarity.

Contribution

It proposes a novel approach to learn sentence embeddings that maintain analogical properties, enhancing answer selection performance over traditional similarity-based methods.

Findings

Embeddings better capture analogical relations than conventional methods.

Analogy-based answer selection outperforms similarity-based techniques.

The method achieves improved results on benchmark datasets.

Abstract

Answer selection aims at identifying the correct answer for a given question from a set of potentially correct answers. Contrary to previous works, which typically focus on the semantic similarity between a question and its answer, our hypothesis is that question-answer pairs are often in analogical relation to each other. Using analogical inference as our use case, we propose a framework and a neural network architecture for learning dedicated sentence embeddings that preserve analogical properties in the semantic space. We evaluate the proposed method on benchmark datasets for answer selection and demonstrate that our sentence embeddings indeed capture analogical properties better than conventional embeddings, and that analogy-based question answering outperforms a comparable similarity-based technique.