Retrieve-and-edit based approaches to structured prediction, where structures associated with retrieved neighbors are edited to form new structures, have recently attracted increased interest. However, much recent work merely conditions on retrieved structures (e.g., in a sequence-to-sequence framework), rather than explicitly manipulating them. We show we can perform accurate sequence labeling by explicitly (and only) copying labels from retrieved neighbors. Moreover, because this copying is label-agnostic, we can achieve impressive performance when transferring to new sequence-labeling tasks without retraining. We additionally consider a dynamic programming approach to sequence labeling in the presence of retrieved neighbors, which allows for controlling the number of distinct (copied) segments used to form a prediction, and leads to both more interpretable and accurate predictions.
翻译:对结构化预测采取基于检索和编辑的方法,与检索的邻居有关的结构被编辑成新的结构,最近引起了越来越多的兴趣。然而,最近许多工作条件只是对检索的结构(例如按顺序排列的框架),而不是对它们进行明确的操纵。我们显示,我们可以通过明确(和仅)复制检索的邻居的标签来进行准确的序列标签。此外,由于这种复制是不可知性的,我们可以在不进行再培训的情况下向新的序列标签任务转移时取得令人印象深刻的成绩。 我们还考虑在检索的邻居在场的情况下采用动态的编程方法对标签进行排序,从而能够控制用来作出预测的不同(复制的)部分的数量,并导致更可解释和准确的预测。