An Attention Mechanism for Answer Selection Using a Combined Global and Local View
Computation and Language
2017-09-21 v4
Abstract
We propose a new attention mechanism for neural based question answering, which depends on varying granularities of the input. Previous work focused on augmenting recurrent neural networks with simple attention mechanisms which are a function of the similarity between a question embedding and an answer embeddings across time. We extend this by making the attention mechanism dependent on a global embedding of the answer attained using a separate network. We evaluate our system on InsuranceQA, a large question answering dataset. Our model outperforms current state-of-the-art results on InsuranceQA. Further, we visualize which sections of text our attention mechanism focuses on, and explore its performance across different parameter settings.
Cite
@article{arxiv.1707.01378,
title = {An Attention Mechanism for Answer Selection Using a Combined Global and Local View},
author = {Yoram Bachrach and Andrej Zukov-Gregoric and Sam Coope and Ed Tovell and Bogdan Maksak and Jose Rodriguez and Conan McMurtie},
journal= {arXiv preprint arXiv:1707.01378},
year = {2017}
}