Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the...
We present a graph-based semi-supervised learning for the question-answering (QA) task for ranking candidate sentences. Using textual entailment analysis, we obtain entailment sco...
Transfer learning addresses the problem of how to leverage knowledge acquired in a source domain to improve the accuracy and speed of learning in a related target domain. This pap...
Lilyana Mihalkova, Tuyen N. Huynh, Raymond J. Moon...
This paper explores the use of the homotopy method for training a semi-supervised Hidden Markov Model (HMM) used for sequence labeling. We provide a novel polynomial-time algorith...
Extraction of entities from ad creatives is an important problem that can benefit many computational advertising tasks. Supervised and semi-supervised solutions rely on labeled da...