arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.01378cs.CL
收藏

一种全局与局部相结合的答案选择注意力机制

An Attention Mechanism for Answer Selection Using a Combined Global and Local View

DigitalGenius(数字天才公司)

Yoram Bachrach, Andrej Zukov-Gregoric, Sam Coope, Ed Tovell, Bogdan Maksak, Jose Rodriguez, Conan McMurtie

摘要:

我们提出了一种新的注意力机制神经为基础的问答,这取决于不同的粒度的输入。以前的工作集中在用简单的注意力机制来增强递归神经网络,这些注意力机制是问题嵌入和答案嵌入之间随时间变化的相似性的函数。我们通过使注意力机制依赖于使用单独的网络获得的答案的全局嵌入来扩展这一点。我们评估我们的系统InsuranceQA,一个大型的问答数据集。我们的模型优于目前最先进的结果保险QA。此外,我们可视化我们的注意力机制关注的文本部分,并探索其在不同参数设置下的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑