Coalescing Global and Local Information for Procedural Text Understanding
This addresses the challenge of tracking entity states in narratives for natural language processing, representing an incremental improvement over prior methods.
The paper tackles procedural text understanding by proposing a model that combines local and global input views with a global output objective to improve both precision and recall, achieving state-of-the-art results on a dataset and enhancing downstream story reasoning.
Procedural text understanding is a challenging language reasoning task that requires models to track entity states across the development of a narrative. A complete procedural understanding solution should combine three core aspects: local and global views of the inputs, and global view of outputs. Prior methods considered a subset of these aspects, resulting in either low precision or low recall. In this paper, we propose Coalescing Global and Local Information (CGLI), a new model that builds entity- and timestep-aware input representations (local input) considering the whole context (global input), and we jointly model the entity states with a structured prediction objective (global output). Thus, CGLI simultaneously optimizes for both precision and recall. We extend CGLI with additional output layers and integrate it into a story reasoning framework. Extensive experiments on a popular procedural text understanding dataset show that our model achieves state-of-the-art results; experiments on a story reasoning benchmark show the positive impact of our model on downstream reasoning.