Learning to Rank Question Answer Pairs with Holographic Dual LSTM Architecture

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.

arXiv commentSIGIR 2017 Full Paper

References in corpus (1)

• Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval

Cited by in corpus (4)

• Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering
• When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges
• A Quantum Many-body Wave Function Inspired Language Modeling Approach
• Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives