Paper: More or less supervised supersense tagging of Twitter

ACL ID S14-1001
Title More or less supervised supersense tagging of Twitter
Venue Joint Conference on Lexical and Computational Semantics
Session
Year 2014
Authors

We present two Twitter datasets annotated with coarse-grained word senses (super- senses), as well as a series of experiments with three learning scenarios for super- sense tagging: weakly supervised learn- ing, as well as unsupervised and super- vised domain adaptation. We show that (a) off-the-shelf tools perform poorly on Twitter, (b) models augmented with em- beddings learned from Twitter data per- form much better, and (c) errors can be reduced using type-constrained inference with distant supervision from WordNet.