One of the major strengths of probabilistic topic modeling is the ability to reveal hidden relations via the analysis of co-occurrence patterns on dyadic observations, such as docu...
This paper demonstrates a new method for leveraging unstructured annotations to infer semantic document properties. We consider the domain of product reviews, which are often anno...
S. R. K. Branavan, Harr Chen, Jacob Eisenstein, Re...
We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
Documents often contain inherently many concepts reflecting specific and generic aspects. To automatically generate a short summary text of documents on similar topics, it is im...
Documents often have inherently parallel structure: they may consist of a text and ries, or an abstract and a body, or parts presenting alternative views on the same problem. Reve...