Sciweavers

NAACL
2004
13 years 6 months ago
Evaluating Content Selection in Summarization: The Pyramid Method
We present an empirically grounded method for evaluating content selection in summarization. It incorporates the idea that no single best model summary for a collection of documen...
Ani Nenkova, Rebecca J. Passonneau
NAACL
2004
13 years 6 months ago
A Salience-Based Approach to Gesture-Speech Alignment
One of the first steps towards understanding natural multimodal language is aligning gesture and speech, so that the appropriate gestures ground referential pronouns in the speech...
Jacob Eisenstein, Chris Mario Christoudias
NAACL
2004
13 years 6 months ago
A Language Modeling Approach to Predicting Reading Difficulty
We demonstrate a new research approach to the problem of predicting the reading difficulty of a text passage, by recasting readability in terms of statistical language modeling. W...
Kevyn Collins-Thompson, James P. Callan
NAACL
2004
13 years 6 months ago
Name Tagging with Word Clusters and Discriminative Training
We present a technique for augmenting annotated training data with hierarchical word clusters that are automatically derived from a large unannotated corpus. Cluster membership is...
Scott Miller, Jethran Guinness, Alex Zamanian
NAACL
2004
13 years 6 months ago
Multiple Similarity Measures and Source-Pair Information in Story Link Detection
State-of-the-art story link detection systems, that is, systems that determine whether two stories are about the same event or linked, are usually based on the cosine-similarity m...
Francine Chen, Ayman Farahat, Thorsten Brants
NAACL
2004
13 years 6 months ago
Robust Reading: Identification and Tracing of Ambiguous Names
A given entity, representing a person, a location or an organization, may be mentioned in text in multiple, ambiguous ways. Understanding natural language requires identifying whe...
Xin Li, Paul Morie, Dan Roth
NAACL
2004
13 years 6 months ago
Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution
We present a coreference resolver called BABAR that uses contextual role knowledge to evaluate possible antecedents for an anaphor. BABAR uses information extraction patterns to i...
David L. Bean, Ellen Riloff
NAACL
2004
13 years 6 months ago
Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization
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. W...
Regina Barzilay, Lillian Lee