Sciweavers

23 search results - page 1 / 5
» Learning to Paraphrase: An Unsupervised Approach Using Multi...
Sort
View
NAACL
2003
13 years 5 months ago
Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment
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 appro...
Regina Barzilay, Lillian Lee
ICASSP
2010
IEEE
13 years 3 months ago
Multiple sequence alignment based bootstrapping for improved incremental word learning
We investigate incremental word learning with few training examples in a Hidden Markov Model (HMM) framework suitable for an interactive learning scenario with little prior knowle...
Irene Ayllól Clemente, Martin Heckmann, Ger...
ACL
2001
13 years 5 months ago
Extracting Paraphrases from a Parallel Corpus
While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. We present ...
Regina Barzilay, Kathleen McKeown
IJCNLP
2005
Springer
13 years 10 months ago
Aligning Needles in a Haystack: Paraphrase Acquisition Across the Web
This paper presents a lightweight method for unsupervised extraction of paraphrases from arbitrary textual Web documents. The method differs from previous approaches to paraphrase...
Marius Pasca, Péter Dienes
ACL
2010
13 years 2 months ago
Learning Script Knowledge with Web Experiments
We describe a novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering. We collect naturallanguage descriptio...
Michaela Regneri, Alexander Koller, Manfred Pinkal