FAQ-based Question Answering via Word Alignment

Abstract

In this paper, we propose a novel word-alignment-based method to solve the FAQ-based question answering task. First, we employ a neural network model to calculate question similarity, where the word alignment between two questions is used for extracting features. Second, we design a bootstrap-based feature extraction method to extract a small set of effective lexical features. Third, we propose a learning-to-rank algorithm to train parameters more suitable for the ranking tasks. Experimental results, conducted on three languages (English, Spanish and Japanese), demonstrate that the question similarity model is more effective than baseline systems, the sparse features bring 5% improvements on top-1 accuracy, and the learning-to-rank algorithm works significantly better than the traditional method. We further evaluate our method on the answer sentence selection task. Our method outperforms all the previous systems on the standard TREC data set.

References in corpus (1)

• Deep Learning for Answer Sentence Selection

Cited by in corpus (6)

• Attentive Pooling Networks
• Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks
• ASBERT: Siamese and Triplet network embedding for open question answering
• Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
• Indirect Supervision for Relation Extraction using Question-Answer Pairs
• A Gated Self-attention Memory Network for Answer Selection