论文标题
Expbert：具有自然语言解释的代表工程
ExpBERT: Representation Engineering with Natural Language Explanations
论文作者
论文摘要
假设我们要指定已婚夫妇通常会在蜜月上进行的感应偏见，以从文本中提取成对的配偶。在本文中，我们允许模型开发人员指定这些类型的归纳偏见为自然语言解释。我们在Multinli上对Bert进行了微调，以``解释''这些解释对输入句子，从而产生了输入的解释引导表示。在三个关系提取任务中，我们的方法expbert匹配了BERT基线，但标记的数据较少3-20倍，并将基线的标签提高3--10 F1点，并具有相同数量的标记数据。
Suppose we want to specify the inductive bias that married couples typically go on honeymoons for the task of extracting pairs of spouses from text. In this paper, we allow model developers to specify these types of inductive biases as natural language explanations. We use BERT fine-tuned on MultiNLI to ``interpret'' these explanations with respect to the input sentence, producing explanation-guided representations of the input. Across three relation extraction tasks, our method, ExpBERT, matches a BERT baseline but with 3--20x less labeled data and improves on the baseline by 3--10 F1 points with the same amount of labeled data.
