论文标题
使用树-RNN和键入依赖项中的句子对识别语义关系
Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies
论文作者
论文摘要
基于依赖树的递归神经网络（树-RNN）在建模句子含义中无处不在，因为它们有效地捕获了非纽伯希单词之间的语义关系。但是，以相同的单词和语法识别语义上不同的句子仍然是对树rnns的挑战。这项工作提出了使用依赖性解析中确定的语法关系类型对依赖性树-RNN（DT-RNN）的改进。我们对语义相关性评分（SRS）的实验和使用病态（涉及组成知识的句子）数据集中识别句子对中的文本含义（RTE）的实验表现出令人鼓舞的结果。该模型通过DT-RNN模型的RTE任务提高了2％的分类精度。结果表明，Pearson和Spearman在模型的相似性得分和人类评分之间的相关性度量高于标准DT-RNN的相关性。
Recursive neural networks (Tree-RNNs) based on dependency trees are ubiquitous in modeling sentence meanings as they effectively capture semantic relationships between non-neighborhood words. However, recognizing semantically dissimilar sentences with the same words and syntax is still a challenge to Tree-RNNs. This work proposes an improvement to Dependency Tree-RNN (DT-RNN) using the grammatical relationship type identified in the dependency parse. Our experiments on semantic relatedness scoring (SRS) and recognizing textual entailment (RTE) in sentence pairs using SICK (Sentence Involving Compositional Knowledge) dataset show encouraging results. The model achieved a 2% improvement in classification accuracy for the RTE task over the DT-RNN model. The results show that Pearson's and Spearman's correlation measures between the model's predicted similarity scores and human ratings are higher than those of standard DT-RNNs.
