One Representation per Word - Does it make Sense for Composition?
Thomas Kober, Julie Weeds, John R. Wilkie, Jeremy Reffin, David R. Weir · 2017
In this paper, we investigate whether an a priori disambiguation of word senses is strictly necessary or whether the meaning of a word in context can be disambiguated through composition alone.We evaluate the performance of off-the-shelf singlevector and multi-sense vector models on a benchmark phrase similarity task and a novel task for word-sense discrimination.We find that single-sense vector models perform as well or better than multi-sense vector models despite arguably less clean elementary representations.Our findings furthermore show that simple composition functions such as pointwise addition are able to recover sense specific information from a single-sense vector model remarkably well.