Applying Deep Learning to Answer Selection: A Study and An Open Task

Abstract

We apply a general deep learning framework to address the non-factoid question answering task. Our approach does not rely on any linguistic tools and can be applied to different languages or domains. Various architectures are presented and compared. We create and release a QA corpus and setup a new QA task in the insurance domain. Experimental results demonstrate superior performance compared to the baseline methods and various technologies give further improvements. For this highly challenging task, the top-1 accuracy can reach up to 65.3% on a test set, which indicates a great potential for practical use.

To appear in the proceedings of ASRU 2015

References in corpus (2)

• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Convolutional Neural Network for Modelling Sentences

Cited by in corpus (26)

• Attentive Pooling Networks
• ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
• On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
• A Deep Look into Neural Ranking Models for Information Retrieval
• WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval
• A survey of Community Question Answering
• Recurrent Neural Network Encoder with Attention for Community Question Answering
• Hierarchical Memory Networks for Answer Selection on Unknown Words
• Analysis of Wikipedia-based Corpora for Question Answering
• A Measure for Dialog Complexity and its Application in Streamlining Service Operations
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• M${}^2$S-Net: Multi-Modal Similarity Metric Learning based Deep Convolutional Network for Answer Selection
• Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge
• RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
• Improved Answer Selection with Pre-Trained Word Embeddings
• Why and How to Pay Different Attention to Phrase Alignments of Different Intensities
• Chinese Medical Question Answer Matching Based on Interactive Sentence Representation Learning
• Evaluating a Generative Adversarial Framework for Information Retrieval
• Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification
• Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering
• GaDei: On Scale-up Training As A Service For Deep Learning
• Exploiting Sentence Embedding for Medical Question Answering
• Representation Learning Models for Entity Search
• Semantic Matching of Documents from Heterogeneous Collections: A Simple and Transparent Method for Practical Applications
• Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
• Automatic Question-Answering Using A Deep Similarity Neural Network