Usenet is a decentralized discussion community predating blogs by decades. Just as there are a wide range of political blogs, many Usenet sub-communities focus on politics. Howeve...
We use search engine results to address a particularly difficult cross-domain language processing task, the adaptation of named entity recognition (NER) from news text to web que...
Previous work on text mining has almost exclusively focused on a single stream. However, we often have available multiple text streams indexed by the same set of time points (call...
Xuanhui Wang, ChengXiang Zhai, Xiao Hu, Richard Sp...
This paper presents a practical machine translation system based on sentence types for economic news stories. Conventional English-to-Japanese machine translation (MT) systems whi...
The social Web is transforming the way information is created and distributed. Authoring tools, e.g., blog publishing services, enable users to quickly and easily publish content,...