2017
EMNLP
EMNLP 2017
Revisiting Selectional Preferences for Coreference Resolution
Abstract
AbstractSelectional preferences have long been claimed to be essential for coreference resolution. However, they are modeled only implicitly by current coreference resolvers. We propose a dependency-based embedding model of selectional preferences which allows fine-grained compatibility judgments with high coverage. Incorporating our model improves performance, matching state-of-the-art results of a more complex system. However, it comes with a cost that makes it debatable how worthwhile are such improvements.
🌉
Interdisciplinary Bridge
— Machine Learning and Natural Language Processing
🐣
Hot Topic Early Bird
— embedding model
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Core Methods > Representation Learning
Machine Learning > Core Methods > Embedding Learning
Natural Language Processing > Understanding > Coreference Resolution
Machine Learning > Learning Types > Representation Learning
Natural Language Processing > Applications > Coreference Resolution