Knowledge work in many fields requires examining several aspects of a collection of documents to attain meaningful understanding that is not explicitly available. Despite recent ad...
This paper provides evidence that the use of more unlabeled data in semi-supervised learning can improve the performance of Natural Language Processing (NLP) tasks, such as part-o...
A Question Answering (QA) system aims to return exact answers to natural language questions. While today information retrieval techniques are quite successful at locating within l...
User generated content and social media (in the form of blogs, wikis, online video, microblogs, etc) are proliferating online. Grapevine conducts large scale data analysis on the ...
Albert Angel, Nick Koudas, Nikos Sarkas, Divesh Sr...
Graphics detection and recognition are fundamental research problems in document image analysis and retrieval. As one of the most pervasive graphical elements in business and gove...