Neural Generative Question Answering
This addresses the challenge of automated question answering for users needing quick factual information, but it is incremental as it builds on existing encoder-decoder frameworks.
The paper tackles the problem of generating answers to factoid questions by developing an end-to-end neural network model that queries a knowledge base, and it shows the model outperforms embedding-based and neural dialogue models on question answering tasks.
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.