We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
Curated databases represent a substantial amount of effort by a dedicated group of people to produce a definitive description of some subject area. The value of curated databases ...
Currently, there is an increasing effort to provide various personalized services on museum web sites. This paper presents an approach for determining user interests in a museum c...
We describe Dispute Finder, a browser extension that alerts a user when information they read online is disputed by a source that they might trust. Dispute Finder examines the tex...
Accurate estimation of information retrieval evaluation metrics such as average precision require large sets of relevance judgments. Building sets large enough for evaluation of r...