Crossing Variational Autoencoders for Answer Retrieval

TL;DR

This paper introduces a novel cross variational auto-encoder approach for answer retrieval that jointly models question-answer pairs, improving alignment and semantic understanding for better retrieval accuracy.

Contribution

The paper proposes a new cross variational auto-encoder framework that generates questions and answers mutually, capturing aligned semantics more effectively than previous methods.

Findings

Outperforms state-of-the-art on SQuAD dataset

Enhances question-answer semantic alignment

Improves answer retrieval accuracy

Abstract

Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semantics between question and answer. In this work, we propose to cross variational auto-encoders by generating questions with aligned answers and generating answers with aligned questions. Experiments show that our method outperforms the state-of-the-art answer retrieval method on SQuAD.