Neural Models for Reasoning over Multiple Mentions using Coreference
This addresses the challenge of long-range dependency handling in NLP tasks like reading comprehension, though it is incremental as it builds on existing models.
The paper tackled the problem of aggregating information from multiple distant entity mentions in NLP by introducing a recurrent layer biased towards coreferent dependencies, which improved performance on Wikihop, LAMBADA, and bAbi AI tasks, especially with scarce training data.
Many problems in NLP require aggregating information from multiple mentions of the same entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks. We present a recurrent layer which is instead biased towards coreferent dependencies. The layer uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster. Incorporating this layer into a state-of-the-art reading comprehension model improves performance on three datasets -- Wikihop, LAMBADA and the bAbi AI tasks -- with large gains when training data is scarce.