Greeting,
This week Joseph Turian will talk about his recent ACL paper. Hope to see you all there.
Date and Time: Thursday August 12th, 15h00 Location: LISA lab (AA3195)
Title and Abstract:
Word representations: A simple and general method for semi-supervised learning
If we take an existing supervised NLP system, a simple and general way to improve accuracy is to use unsupervised word representations as extra word features. We evaluate Brown clusters, Collobert + Weston (2008) embeddings, and HLBL (Mnih + Hinton, 2009) embeddings of words on both NER and chunking. We use near state-of-the-art supervised baselines, and find that each of the three word representations improves the accuracy of these baselines. We find further improvements by combining different word representations. You can download our word features, for off-the-shelf use in existing NLP systems, as well as our code, here: http://metaoptimize.com/projects/wordreprs/
Cheers, Aaron
Afficher les réponses par date