TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Question Answering	WikiHop	Coref-GRU	Test	59.3	# 7

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/neural-models-for-reasoning-over-multiple/question-answering-on-wikihop)](https://paperswithcode.com/sota/question-answering-on-wikihop?p=neural-models-for-reasoning-over-multiple)`

Neural Models for Reasoning over Multiple Mentions using Coreference

NAACL 2018 · Bhuwan Dhingra, Qiao Jin, Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov ·

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.