Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
Recommender Systems allow people to find the resources they need by making use of the experiences and opinions of their nearest neighbours. Costly annotations by experts are replac...
Hierarchy fundamentally shapes how we act at work. In this paper, we explore the relationship between the words people write in workplace email and the rank of the email’s recip...
Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constitu...
Entity Recognition (ER) is a key component of relation extraction systems and many other natural-language processing applications. Unfortunately, most ER systems are restricted to...