CLDec 4, 2015

Neural Generative Question Answering

arXiv:1512.01337v4217 citations
Originality Incremental advance
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes