Procedural Text Understanding via Scene-Wise Evolution
Keywords:Speech & Natural Language Processing (SNLP)
AbstractProcedural text understanding requires machines to reason about entity states within the dynamical narratives. Current procedural text understanding approaches are commonly 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 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 Scene Graph Reasoner (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.
How to Cite
Tang, J., Lin, H., Liao, M., Lu, Y., Han, X., Sun, L., Xie, W., & Xu, J. (2022). Procedural Text Understanding via Scene-Wise Evolution. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11367-11375. https://doi.org/10.1609/aaai.v36i10.21388
AAAI Technical Track on Speech and Natural Language Processing