Neural Generative Question Answering

Abstract

This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifically, the model is built on the encoder-decoder framework for sequence-to-sequence learning, while equipped with the ability to enquire the knowledge-base, and is trained on a corpus of question-answer pairs, with their associated triples in the knowledge-base. Empirical study shows the proposed model can effectively deal with the variations of questions and answers, and generate right and natural answers by referring to the facts in the knowledge-base. The experiment on question answering demonstrates that the proposed model can outperform an embedding-based QA model as well as a neural dialogue model trained on the same data.

Accepted by IJCAI 2016

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Theano: new features and speed improvements
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Large-scale Simple Question Answering with Memory Networks
• Neural Responding Machine for Short-Text Conversation
• Open Question Answering with Weakly Supervised Embedding Models
• Neural Enquirer: Learning to Query Tables with Natural Language

Cited by in corpus (16)

• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• A Neural Knowledge Language Model
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Neural Machine Translation with External Phrase Memory
• A Unified Query-based Generative Model for Question Generation and Question Answering
• Proactive Human-Machine Conversation with Explicit Conversation Goals
• Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method
• Review Conversational Reading Comprehension
• LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues
• Deep Active Learning for Dialogue Generation
• Natural Language Generation with Neural Variational Models
• Why are Sequence-to-Sequence Models So Dull? Understanding the Low-Diversity Problem of Chatbots
• Coupling Distributed and Symbolic Execution for Natural Language Queries
• ReDecode Framework for Iterative Improvement in Paraphrase Generation
• Content-Based Table Retrieval for Web Queries
• Approach for Semi-automatic Construction of Anti-infective Drug Ontology Based on Entity Linking