Portfolio selection is concerned with optimization of capital allocation to a large number of securities. In portfolio selection, risk analysis is one of the most important topics and research on quantitative definition of risk remains core of the topic. This paper proposes a novel risk definition for portfolio selection with uncertain returns. A risk curve is introduced and a new safe criterio...

Dirichlet Multinomial Regression (DMR) and other supervised topic models can incorporate arbitrary document-level features to inform topic priors. However, their ability to model corpora are limited by the representation and selection of these features – a choice the topic modeler must make. Instead, we seek models that can learn the feature representations upon which to condition topic selecti...

The focus of the blog distillation task is finding blogs with a principle, recurring interest in a specific topic. For this task, we considered a blog as a collection of postings and used resource selection approaches. Further, we investigated techniques that penalized general blogs and combined resource selection techniques. This combination demonstrated significant improvements over baselines.

Many natural language processing (NLP) tasks involve multiple inputs and/or outputs, which are strongly correlated to each other. We call such problems “interdependent decision problems (IDPs)” since the decisions on outputs should be interdependent to each other. In this thesis, we focus on three typical IDPs in NLP and investigate discriminative learning methods for these problems. The first ...

Feature selection is an important topic that has been widely studied in data science.

Retrieving documents by subject matter is the general goal of information retrieval and other content access systems. There are other aspects of textual content, however, which form equally valid selection critieria. One such aspect is that of sentiment or polarity indicating the users opinion or emotional relationship with some topic. Recent work in this area has treated polarity effectively a...