arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.04348cs.CL
收藏

交互空间上的自然语言推理

Natural Language Inference over Interaction Space

New York University(纽约大学);Horizon Robotics, Inc.(地平线机器人技术有限公司(Horizon Robotics, Inc.))

Yichen Gong, Heng Luo, Jian Zhang

摘要:

自然语言推理(NLI)任务要求智能体确定自然语言前提和自然语言假设之间的逻辑关系。我们介绍了交互式推理网络(IIN),一类新的神经网络架构,能够实现高层次的理解的句子对分层提取的语义特征,从交互空间。我们发现,一个交互张量(注意力权重)包含语义信息来解决自然语言推理,和一个密集的交互张量包含更丰富的语义信息。这种架构的一个实例,密集交互式推理网络(DIIN),展示了国家的最先进的性能上的大规模NLI copora和大规模NLI相似的语料库。值得注意的是,相对于最强的已发布系统,DIIN在具有挑战性的多类型NLI(MultiNLI)数据集上实现了超过20%的错误减少。

英文摘要:

Natural Language Inference (NLI) task requires an agent to determine the logical relationship between a natural language premise and a natural language hypothesis. We introduce Interactive Inference Network (IIN), a novel class of neural network architectures that is able to achieve high-level understanding of the sentence pair by hierarchically extracting semantic features from interaction space. We show that an interaction tensor (attention weight) contains semantic information to solve natural language inference, and a denser interaction tensor contains richer semantic information. One instance of such architecture, Densely Interactive Inference Network (DIIN), demonstrates the state-of-the-art performance on large scale NLI copora and large-scale NLI alike corpus. It's noteworthy that DIIN achieve a greater than 20% error reduction on the challenging Multi-Genre NLI (MultiNLI) dataset with respect to the strongest published system.

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。

↑