300 citations · 404 across the 3 of their papers we have counts for
3 papers
cs.CL2004★ 300 cited
Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization
Regina Barzilay, Lillian Lee
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We…
cs.CL2003★ 98 cited
Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment
Regina Barzilay, Lillian Lee
We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach…
cs.CL2002★ 6 cited
Bootstrapping Lexical Choice via Multiple-Sequence Alignment
Regina Barzilay, Lillian Lee
An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically,…