Leveraging Annotators' Gaze Behaviour for Coreference Resolution
Joe Cheri, Abhijit K. Mishra, Pushpak Bhattacharyya · 2016
This paper aims at utilizing cognitive information obtained from the eye movements behavior of annotators for automatic coreference resolution.We first record eye-movement behavior of multiple annotators resolving coreferences in 22 documents selected from MUC dataset.By inspecting the gaze-regression profiles of our participants, we observe how regressive saccades account for selection of potential antecedents for a certain anaphoric mention.Based on this observation, we then propose a heuristic to utilize gaze data to prune mention pairs in mention-pair model, a popular paradigm for automatic coreference resolution.Consistent improvement in accuracy across several classifiers is observed with our heuristic, demonstrating why cognitive data can be useful for a difficult task like coreference resolution.