Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited from such knowledge transfer because of its distinct formulation, i.e., tracking the event flow while following structural constraints. State-of-the-art entity tracking approaches either design complicated model architectures or rely on task-specific pre-training to achieve good results. To this end, we propose MeeT, a Multi-task learning-enabled entity Tracking approach, which utilizes knowledge gained from general domain tasks to improve entity tracking. Specifically, MeeT first fine-tunes T5, a pre-trained multi-task learning model, with entity tracking-specialized QA formats, and then employs our customized decoding strategy to satisfy the structural constraints. MeeT achieves state-of-the-art performances on two popular entity tracking datasets, even though it does not require any task-specific architecture design or pre-training.

翻译：多任务学习通过跨任务知识迁移在通用自然语言处理任务中取得了显著进展。然而，由于程序文本中的实体追踪具有独特的建模形式——即在遵循结构约束的同时追踪事件流——该方法尚未从这种知识迁移中受益。现有最优的实体追踪方法要么设计复杂的模型架构，要么依赖任务特定的预训练来获得良好效果。为此，我们提出MeeT——一种基于多任务学习的实体追踪方法，通过利用通用领域任务中获得的知识提升实体追踪性能。具体而言，MeeT首先使用实体追踪专用的问答格式对预训练的多任务学习模型T5进行微调，然后采用我们定制的解码策略来满足结构约束。尽管MeeT无需任何任务特定的架构设计或预训练，它在两个主流实体追踪数据集上仍取得了最优性能。