An Unsupervised Model with Attention Autoencoders for Question Retrieval

TL;DR

This paper introduces an unsupervised question retrieval model using attention autoencoders that effectively combines semantic and lexical features, achieving competitive results without relying on labeled training data.

Contribution

The paper presents a novel unsupervised framework with attention autoencoders for semantic question matching, outperforming supervised methods on benchmark datasets.

Findings

Achieves comparable performance to supervised models on SemEval-2016.

Outperforms state-of-the-art in SemEval-2017.

Introduces attention autoencoders for question semantic representation.

Abstract

Question retrieval is a crucial subtask for community question answering. Previous research focus on supervised models which depend heavily on training data and manual feature engineering. In this paper, we propose a novel unsupervised framework, namely reduced attentive matching network (RAMN), to compute semantic matching between two questions. Our RAMN integrates together the deep semantic representations, the shallow lexical mismatching information and the initial rank produced by an external search engine. For the first time, we propose attention autoencoders to generate semantic representations of questions. In addition, we employ lexical mismatching to capture surface matching between two questions, which is derived from the importance of each word in a question. We conduct experiments on the open CQA datasets of SemEval-2016 and SemEval-2017. The experimental results show that our unsupervised model obtains comparable performance with the state-of-the-art supervised methods in SemEval-2016 Task 3, and outperforms the best system in SemEval-2017 Task 3 by a wide margin.