@InProceedings{bhat-sproat:2009:ACLIJCNLP, author = {Bhat, Suma and Sproat, Richard}, title = {Knowing the Unseen: Estimating Vocabulary Size over Unseen Samples}, booktitle = {Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP}, month = {August}, year = {2009}, address = {Suntec, Singapore}, publisher = {Association for Computational Linguistics}, pages = {109--117}, url = {http://www.aclweb.org/anthology/P/P09/P09-1013} }