Word sense disambiguation (WSD) is a long-standing problem in naturallanguage processing . A significant challenge in supervised all-words WSD is to classify among senses for a majority of words that lie in the long-taildistribution . In this work, we proposeMetricWSD, a non-parametric few-shot learning approach to mitigate this dataimbalance issue . By learning to compute distances among the senses of a givenword through episodic training, MetricsWSD transfers knowledge (a learned metricspace) from high-frequency words to infrequent ones . Our analysis further validates that infrequent wordsand senses enjoy significant improvement. Our analysisFurther validating that Infrequent words and senses enjoy significantly improvement. In fact, Metric WSD obtains strong performance against parametricalternatives

Author(s) : Howard Chen, Mengzhou Xia, Danqi Chen

Links : PDF - Abstract

Code :
Coursera

Keywords : senses - words - learning - wsd - infrequent -

Leave a Reply

Your email address will not be published. Required fields are marked *