NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
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 ...
NAACL
2004
14 years 2 months ago
2004
NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
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...
NAACL
2004
14 years 2 months ago
2004
