arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09400cs.CL
收藏

Transformer语言模型中桥接推理的探讨

Probing for Bridging Inference in Transformer Language Models

University of Lille(里尔大学);INRIA Lille(法国国家信息与自动化研究所里尔分部);CNRS(法国国家科学研究中心);Centrale Lille(里尔中央理工学院);IBM Research Europe(IBM欧洲研究院)

Onkar Pandit, Yufang Hou

摘要:

我们探测用于桥接推理的预训练的Transformer语言模型。我们首先考察了BERT中的个体注意头,发现与低层和中层注意头相比,高层注意头更显著地关注桥接关系,并且很少有特定的注意头持续地关注桥接关系。更重要的是,我们认为语言模型作为一个整体,在我们的第二种方法,桥接回指的决议制定为一个掩蔽的令牌预测任务(过完形填空测试)。我们的公式产生了乐观的结果,没有任何微调,这表明预训练的语言模型基本上捕获桥接推理。进一步的研究表明,回指先行词与提供给语言模型的上下文之间的距离在推理中起着重要的作用。

英文摘要:

We probe pre-trained transformer language models for bridging inference. We first investigate individual attention heads in BERT and observe that attention heads at higher layers prominently focus on bridging relations in-comparison with the lower and middle layers, also, few specific attention heads concentrate consistently on bridging. More importantly, we consider language models as a whole in our second approach where bridging anaphora resolution is formulated as a masked token prediction task (Of-Cloze test). Our formulation produces optimistic results without any fine-tuning, which indicates that pre-trained language models substantially capture bridging inference. Our further investigation shows that the distance between anaphor-antecedent and the context provided to language models play an important role in the inference.

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。

↑