In this paper, we demonstrate that accurate machine translation is possible without the concept of “words,” treating MT as a problem of transformation between character string...
Graham Neubig, Taro Watanabe, Shinsuke Mori, Tatsu...
We illustrate and explain problems of n-grams-based machine translation (MT) metrics (e.g. BLEU) when applied to morphologically rich languages such as Czech. A novel metric SemPO...
In this paper, we describe area of recommender systems, with focus on user preference learning problem. We describe such system and identify some interesting problems. We will comp...
Although Support Vector Machines (SVMs) have been successfully applied to solve a large number of classification and regression problems, they suffer from the catastrophic forgetti...
We report in this paper our work on accurately generating case markers and suffixes in English-to-Hindi SMT. Hindi is a relatively free word-order language, and makes use of a com...