Learn More
We report on work in progress on extracting lexical simplifications (e.g., " collaborate " → " work together "), focusing on utilizing edit histories in Simple English Wikipedia for this task. We consider two main approaches: (1) deriving simplification probabilities via an edit model that accounts for a mixture of different operations, and (2) using(More)
This paper studies generation of descriptive sentences from densely annotated images. Previous work studied generation from automatically detected visual information but produced a limited class of sentences , hindered by currently unreliable recognition of activities and attributes. Instead , we collect human annotations of objects , parts, attributes and(More)
Many online human activities leave digital traces that are recorded in natural-language format. The exploitation of this unprecedented resource under a computational framework can bring a phase transition in our understanding of human social behavior and shape the future of social media systems. This thesis describes a computational approach to an(More)
Dedication To my cat Pupu. iii Acknowledgments Studying for a PhD and moving to a foreign country has been a valuable and exciting experience. I could not have succeeded without the advice, support and influence of many colleagues, friends and family. My thanks are due first and foremost to my advisor, Ralph Grishman, for his guidance and continuous support(More)
Obtaining common sense knowledge using current information extraction techniques is extremely challenging. In this work, we instead propose to derive simple common sense statements from fully annotated object detection corpora such as the Microsoft Common Objects in Context dataset. We show that many thousands of common sense facts can be extracted from(More)
Language can describe our visual world at many levels, including not only what is literally there but also the sentiment that it invokes. In this paper, we study visual language, both literal and sentimental, that describes the overall appearance and style of virtual characters. Sentimental properties, including labels such as " youthful " or " country(More)
  • 1