Abstract This paper describes a hybrid statistical and knowledge-based inforQ1 mation extraction model, able to extract entities and relations at the sentence level. The model atte...
We present here a method for automatically projecting structural information across translations, including canonical citation structure (such as chapters and sections), speaker i...
Abstract. Anyone offering content in a digital library is naturally interested in assessing its performance: how well does my system meet the users' information needs? Standar...
This paper describes AutoTag, a tool which suggests tags for weblog posts using collaborative filtering methods. An evaluation of AutoTag on a large collection of posts shows good...
We address the task of answering natural language questions by using the large number of Frequently Asked Questions (FAQ) pages available on the web. The task involves three steps...