论文标题
探测神经关系提取中句子级表示的语言特征
Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction
论文作者
论文摘要
尽管最近取得了进展，但对最新神经关系提取（RE）模型所捕获的特征知之甚少。通用方法在对关系进行分类之前，以实体提及的条件进行编码。但是，任务的复杂性使得很难理解编码器架构和支持语言知识如何影响编码器所学的特征。我们介绍了14项针对与RE相关的语言属性的探测任务，我们使用它们来研究由40多个不同的编码器体系结构和语言特征组合所学到的表示，在两个数据集上训练了Tacred和Semeval 2010 Task 8。我们发现，由体系结构和语言功能的包含在探针任务中表达出来的偏见。例如，添加上下文化的单词表示形式大大提高了探测任务的性能，重点是命名实体和言论部分信息，并在RE中产生更好的结果。相比之下，实体掩盖可改善RE，但大大降低了与实体类型相关的探测任务的性能。
Despite the recent progress, little is known about the features captured by state-of-the-art neural relation extraction (RE) models. Common methods encode the source sentence, conditioned on the entity mentions, before classifying the relation. However, the complexity of the task makes it difficult to understand how encoder architecture and supporting linguistic knowledge affect the features learned by the encoder. We introduce 14 probing tasks targeting linguistic properties relevant to RE, and we use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets, TACRED and SemEval 2010 Task 8. We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance. For example, adding contextualized word representations greatly increases performance on probing tasks with a focus on named entity and part-of-speech information, and yields better results in RE. In contrast, entity masking improves RE, but considerably lowers performance on entity type related probing tasks.
