论文标题
编码器模型的排名一编辑
Rank-One Editing of Encoder-Decoder Models
论文作者
论文摘要
诸如神经机器翻译（NMT）等任务的序列模型的大序列通常经过数亿个样本训练。但是，培训只是模型生命周期的起源。随着新的要求或不足之处的众所周知，模型的现实部署需要进一步的行为适应。通常，在模型行为的空间中，行为删除请求是通过模型再培训来解决的，而模型进行了列表以解决行为添加请求，这两个过程都是基于数据的模型干预的实例。在这项工作中，我们提出了一项初步研究，该研究调查了排名一编辑，作为一种直接干预方法，用于在编码器删除变压器模型中的行为删除请求。我们为NMT提出了四个编辑任务，并表明所提出的编辑算法达到了高效率，同时仅需要一个积极的实例来修复错误（负）模型行为。
Large sequence to sequence models for tasks such as Neural Machine Translation (NMT) are usually trained over hundreds of millions of samples. However, training is just the origin of a model's life-cycle. Real-world deployments of models require further behavioral adaptations as new requirements emerge or shortcomings become known. Typically, in the space of model behaviors, behavior deletion requests are addressed through model retrainings whereas model finetuning is done to address behavior addition requests, both procedures being instances of data-based model intervention. In this work, we present a preliminary study investigating rank-one editing as a direct intervention method for behavior deletion requests in encoder-decoder transformer models. We propose four editing tasks for NMT and show that the proposed editing algorithm achieves high efficacy, while requiring only a single instance of positive example to fix an erroneous (negative) model behavior.
