Collocation translation is important for machine translation and many other NLP tasks. Unlike previous methods using bilingual parallel corpora, this paper presents a new method f...
We present Penumbra Limit Maps, a technique for rendering soft shadows from a modified shadow map. The shadow representation used by our method has excellent interpolation propert...
In most research on concept acquisition from corpora, concepts are modeled as vectors of relations extracted from syntactic structures. In the case of modifiers, these relations o...
All questions are implicitly associated with an expected answer type. Unlike previous approaches that require a predefined set of question types, we present a method for dynamical...
We propose a supervised, two-phase framework to address the problem of paraphrase recognition (PR). Unlike most PR systems that focus on sentence similarity, our framework detects...