Entity Tracking Improves Cloze-style Reading Comprehension
This addresses the challenge of entity reference tracking in reading comprehension for AI models, though it is incremental as it builds on existing neural methods.
The paper tackled the problem of entity tracking in cloze-style reading comprehension, showing that adding entity features and a multi-task tracking objective improves performance, outperforming previous state of the art on the LAMBADA dataset, especially on difficult entity examples.
Reading comprehension tasks test the ability of models to process long-term context and remember salient information. Recent work has shown that relatively simple neural methods such as the Attention Sum-Reader can perform well on these tasks; however, these systems still significantly trail human performance. Analysis suggests that many of the remaining hard instances are related to the inability to track entity-references throughout documents. This work focuses on these hard entity tracking cases with two extensions: (1) additional entity features, and (2) training with a multi-task tracking objective. We show that these simple modifications improve performance both independently and in combination, and we outperform the previous state of the art on the LAMBADA dataset, particularly on difficult entity examples.