Developing better methods for segmenting continuous text into words is important for improving the processing of Asian languages, and may shed light on how humans learn to segment...
Sharon Goldwater, Thomas L. Griffiths, Mark Johnso...
This paper presents a prosodic phrasing model for Korean to be used in a text-to-speech synthesis (TTS) system. Read text corpora were morpho-syntactically parsed and prosodically...
As part of the Language Observatory Project [4], we have been crawling all the web space since 2004. We have collected terabytes of data mostly from Asian and African ccTLDs. In t...
Rizza Camus Caminero, Pavol Zavarsky, Yoshiki Mika...
We study the problem of multivariate integration on the unit cube for unbounded integrands. Our study is motivated by problems in statistics and mathematical finance, where unboun...
Benjamin J. Waterhouse, Frances Y. Kuo, Ian H. Slo...
We present a video recognition system of a “Go” TV program. It generates a Go play record automatically from a broadcast of Go played by human professionals. “Go” is the a...