Incremental dialogue model components produce a sequence of output prefixes based on incoming input. Mistakes can occur due to local ambiguities or to wrong hypotheses, making the ability to revise past outputs a desirable property that can be governed by a policy. In this work, we formalise and characterise edits and revisions in incremental sequence labelling and propose metrics to evaluate revision policies. We then apply our methodology to profile the incremental behaviour of three Transformer-based encoders in various tasks, paving the road for better revision policies.

翻译：增量对话模型组件会根据输入生成一系列输出前缀。由于局部歧义或错误假设可能导致错误，因此具备修正历史输出的能力成为一项可取特性，该能力可由相应策略加以调控。本研究对增量序列标注中的编辑与修订操作进行形式化定义与特征刻画，并提出评估修订策略的指标。我们随后将该方法应用于分析三种基于Transformer的编码器在不同任务中的增量行为，为制定更优修订策略奠定基础。