arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.03316cs.CLcs.NE
收藏

神经阅读理解中的答案与错误分离

Separating Answers from Queries for Neural Reading Comprehension

Language Technology Lab, DFKI(DFKI 语言技术实验室)

Dirk Weissenborn

摘要:

我们提出了一种新的神经架构回答查询,旨在最佳地利用明确的支持形式的问答记忆。我们的模型能够细化和更新给定的查询,同时单独积累预测答案的证据。它的架构反映了这种分离,具有专用的嵌入矩阵和松散连接的信息路径(模块),用于更新查询和积累证据。这种职责的分离有效地简化了查询相关支持的搜索和答案的预测。在最近的阅读理解基准数据集上,我们的模型取得了最先进的结果。定性分析表明,该模型有效地积累了加权证据的查询和多个支持检索周期,从而导致一个强大的答案预测。

英文摘要:

We present a novel neural architecture for answering queries, designed to optimally leverage explicit support in the form of query-answer memories. Our model is able to refine and update a given query while separately accumulating evidence for predicting the answer. Its architecture reflects this separation with dedicated embedding matrices and loosely connected information pathways (modules) for updating the query and accumulating evidence. This separation of responsibilities effectively decouples the search for query related support and the prediction of the answer. On recent benchmark datasets for reading comprehension, our model achieves state-of-the-art results. A qualitative analysis reveals that the model effectively accumulates weighted evidence from the query and over multiple support retrieval cycles which results in a robust answer prediction.

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。

↑