arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.14271cs.IR
收藏

带解释的关系抽取

Relation Extraction with Explanation

Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini, Prasad Tadepalli

摘要:

最近的神经模型与远程监督的关系抽取减轻的影响,不相关的句子在一个袋子里学习的重要性权重的句子。到目前为止,努力集中在提高提取的准确性,但很少有人知道他们的解释。在这项工作中,我们注释了一个测试集与地面真理的解释水平,以评估质量的解释所提供的关系抽取模型。我们证明,替换的实体提到的句子与其细粒度的实体类型,不仅提高了提取的准确性,但也提高了解释。我们还建议自动生成“干扰”的句子,以增加袋和训练模型忽略干扰。对广泛使用的FB-NYT数据集的评估表明,我们的方法在提高模型可解释性的同时,实现了新的最先进的准确性。

英文摘要:

Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Efforts thus far have focused on improving extraction accuracy but little is known about their explainability. In this work we annotate a test set with ground-truth sentence-level explanations to evaluate the quality of explanations afforded by the relation extraction models. We demonstrate that replacing the entity mentions in the sentences with their fine-grained entity types not only enhances extraction accuracy but also improves explanation. We also propose to automatically generate "distractor" sentences to augment the bags and train the model to ignore the distractors. Evaluations on the widely used FB-NYT dataset show that our methods achieve new state-of-the-art accuracy while improving model explainability.

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。

↑