基于场景进化的过程文本理解
Procedural Text Understanding via Scene-Wise Evolution
摘要：
程序化文本理解需要机器对动态叙述中的实体状态进行推理。当前的过程式文本理解方法通常是\textbf{entity-wise}，其分别跟踪每个实体并独立地预测每个实体的不同状态。这样的实体智慧范式没有考虑实体和它们的状态之间的交互。在本文中，我们提出了一个新的\textbf{scene-wise}范式的过程文本理解，联合跟踪状态的所有实体在一个场景的方式。基于这种范式，我们提出了\textbf{S} cene \textbf{G}和\textbf{R} easoner（\textbf{SGR}），它引入了一系列动态演变的场景图，共同制定实体，状态及其关联的整个叙事的演变。通过这种方式，所有实体和状态之间的深层交互可以联合捕获并同时从场景图中导出。实验表明，SGR不仅达到了新的最先进的性能，而且显着加快推理的速度。
英文摘要：
Procedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly \textbf{entity-wise}, which separately track each entity and independently predict different states of each entity. Such an entity-wise paradigm does not consider the interaction between entities and their states. In this paper, we propose a new \textbf{scene-wise} paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner. Based on this paradigm, we propose \textbf{S}cene \textbf{G}raph \textbf{R}easoner (\textbf{SGR}), which introduces a series of dynamically evolving scene graphs to jointly formulate the evolution of entities, states and their associations throughout the narrative. In this way, the deep interactions between all entities and states can be jointly captured and simultaneously derived from scene graphs. Experiments show that SGR not only achieves the new state-of-the-art performance but also significantly accelerates the speed of reasoning.
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。
