We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...
We propose a variation of the SO-PMI algorithm for Japanese, for use in Weblog Opinion Mining. SO-PMI is an unsupervised approach proposed by Turney that has been shown to work we...
As natural language understanding research advances towards deeper knowledge modeling, the tasks become more and more complex: we are interested in more nuanced word characteristi...
Radu Florian, Hongyan Jing, Nanda Kambhatla, Imed ...
We present an extension of phrase-based statistical machine translation models that enables the straight-forward integration of additional annotation at the word-level — may it ...
The Chernoff-Hoeffding bounds are fundamental probabilistic tools. An elementary approach is presented to obtain a Chernoff-type upper-tail bound for the number of prime factors o...