arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 1801.01641cs.IRcs.CL
收藏

aNMM:基于注意力的神经匹配模型对简短答案文本进行排序

aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)

Liu Yang, Qingyao Ai, Jiafeng Guo, W. Bruce Croft

摘要:

作为基于特征工程的问答方法的替代方案,最近已经提出了诸如卷积神经网络(CNN)和长短期记忆模型(LSTM)的深度学习方法,用于问题和答案的语义匹配。然而,为了达到良好的效果,这些模型已经与额外的功能相结合,如单词重叠或BM 25分数。如果没有这种组合,这些模型的表现明显不如基于语言特征工程的方法。在本文中,我们提出了一个基于注意力的神经匹配模型的排名简答文本。我们采用值共享的加权方案,而不是位置共享的加权方案,以结合不同的匹配信号,并结合使用问题注意力网络的问题术语重要性学习。使用流行的基准TREC QA数据,我们表明,相对简单的aNMM模型可以显着优于其他神经网络模型,已用于问答任务,并与模型相结合的其他功能是有竞争力的。当aNMM与其他功能相结合时,它的性能优于所有基线。

英文摘要:

As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term Memory Models (LSTMs) have recently been proposed for semantic matching of questions and answers. To achieve good results, however, these models have been combined with additional features such as word overlap or BM25 scores. Without this combination, these models perform significantly worse than methods based on linguistic feature engineering. In this paper, we propose an attention based neural matching model for ranking short answer text. We adopt value-shared weighting scheme instead of position-shared weighting scheme for combining different matching signals and incorporate question term importance learning using question attention network. Using the popular benchmark TREC QA data, we show that the relatively simple aNMM model can significantly outperform other neural network models that have been used for the question answering task, and is competitive with models that are combined with additional features. When aNMM is combined with additional features, it outperforms all baselines.

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。

↑