需要哪些知识?面向kNN-MT领域自适应的可解释记忆
What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation
摘要:
kNN-MT通过构建外部语义库,将所有目标语言的语义标记保存在并行语料库中,为领域自适应提供了一种新的范例。因此,构造的数据库通常很大,并且可能是冗余的。在本文中,我们调查这种方法的可解释性问题:什么知识的NMT模型需要?我们提出了局部正确性(LAC)的概念作为一个新的角度,它描述了潜在的翻译正确性为一个单一的条目,并为一个给定的邻居。实证研究表明,我们的研究成功地找到了NMT模型容易失败的条件,需要相关的知识。在六个不同的目标领域和两个语言对上的实验表明,根据局部正确性进行剪枝,为kNN-MT领域自适应带来了更轻和更可解释的记忆。
英文摘要:
kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a result, the constructed datastore is usually large and possibly redundant. In this paper, we investigate the interpretability issue of this approach: what knowledge does the NMT model need? We propose the notion of local correctness (LAC) as a new angle, which describes the potential translation correctness for a single entry and for a given neighborhood. Empirical study shows that our investigation successfully finds the conditions where the NMT model could easily fail and need related knowledge. Experiments on six diverse target domains and two language-pairs show that pruning according to local correctness brings a light and more explainable memory for kNN-MT domain adaptation.
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。