Learning to Rank Question Answer Pairs with Holographic Dual LSTM Architecture

TL;DR

This paper introduces HD-LSTM, a deep learning model that uses holographic composition to effectively rank question-answer pairs, outperforming existing neural architectures without extensive feature engineering.

Contribution

The paper proposes a novel holographic composition method integrated with LSTM for question-answer ranking, offering scalable and rich representations with fewer parameters.

Findings

HD-LSTM outperforms other neural models on benchmark datasets.

Holographic composition is more effective than neural tensor layers.

Model requires no extensive feature engineering.

Abstract

We describe a new deep learning architecture for learning to rank question answer pairs. Our approach extends the long short-term memory (LSTM) network with holographic composition to model the relationship between question and answer representations. As opposed to the neural tensor layer that has been adopted recently, the holographic composition provides the benefits of scalable and rich representational learning approach without incurring huge parameter costs. Overall, we present Holographic Dual LSTM (HD-LSTM), a unified architecture for both deep sentence modeling and semantic matching. Essentially, our model is trained end-to-end whereby the parameters of the LSTM are optimized in a way that best explains the correlation between question and answer representations. In addition, our proposed deep learning architecture requires no extensive feature engineering. Via extensive experiments, we show that HD-LSTM outperforms many other neural architectures on two popular benchmark QA datasets. Empirical studies confirm the effectiveness of holographic composition over the neural tensor layer.