We describe a new approach to SMT adaptation that weights out-of-domain phrase pairs according to their relevance to the target domain, determined by both how similar to it they a...
— Fundamental to the problem of lifelong machine learning is how to consolidate the knowledge of a learned task within a long-term memory structure (domain knowledge) without the...
While in most planning approaches goals and plans are different objects, it is often useful to specify goals that combine declarative conditions with procedural plans. In this pap...
Abstract. Constraint satisfaction problems provide strong formalism for modeling variety of real life problems. This paper presents a work currently in progress of which the goal i...
We investigate the problem of learning a part-of-speech (POS) lexicon for a resource-poor language, dialectal Arabic. Developing a high-quality lexicon is often the first step tow...