Sciweavers

NAACL
2004
13 years 5 months ago
Exponential Priors for Maximum Entropy Models
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
Joshua Goodman
NAACL
2004
13 years 5 months ago
A Smorgasbord of Features for Statistical Machine Translation
We describe a methodology for rapid experimentation in statistical machine translation which we use to add a large number of features to a baseline system exploiting features from...
Franz Josef Och, Daniel Gildea, Sanjeev Khudanpur,...
NAACL
2004
13 years 5 months ago
What's in a translation rule?
We propose a theory that gives formal semantics to word-level alignments defined over parallel corpora. We use our theory to introduce a linear algorithm that can be used to deriv...
Michel Galley, Mark Hopkins, Kevin Knight, Daniel ...
NAACL
2004
13 years 5 months ago
Predicting Emotion in Spoken Dialogue from Multiple Knowledge Sources
We examine the utility of multiple types of turn-level and contextual linguistic features for automatically predicting student emotions in human-human spoken tutoring dialogues. W...
Katherine Forbes-Riley, Diane J. Litman
NAACL
2004
13 years 5 months ago
The (Non)Utility of Predicate-Argument Frequencies for Pronoun Interpretation
State-of-the-art pronoun interpretation systems rely predominantly on morphosyntactic contextual features. While the use of deep knowledge and inference to improve these models wo...
Andrew Kehler, Douglas E. Appelt, Lara Taylor, Ale...
NAACL
2004
13 years 5 months ago
A Statistical Model for Multilingual Entity Detection and Tracking
Entity detection and tracking is a relatively new addition to the repertoire of natural language tasks. In this paper, we present a statistical language-independent framework for ...
Radu Florian, Hany Hassan, Abraham Ittycheriah, Ho...
NAACL
2004
13 years 5 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 5 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