Sciweavers

NAACL
2010
13 years 2 months ago
Predicting Human-Targeted Translation Edit Rate via Untrained Human Annotators
In the field of machine translation, automatic metrics have proven quite valuable in system development for tracking progress and measuring the impact of incremental changes. Howe...
Omar Zaidan, Chris Callison-Burch
NAACL
2010
13 years 2 months ago
Variational Inference for Adaptor Grammars
Adaptor grammars extend probabilistic context-free grammars to define prior distributions over trees with "rich get richer" dynamics. Inference for adaptor grammars seek...
Shay B. Cohen, David M. Blei, Noah A. Smith
NAACL
2010
13 years 2 months ago
Linguistic Steganography Using Automatically Generated Paraphrases
This paper describes a method for checking the acceptability of paraphrases in context. We use the Google n-gram data and a CCG parser to certify the paraphrasing grammaticality a...
Ching-Yun Chang, Stephen Clark
NAACL
2010
13 years 2 months ago
Learning about Voice Search for Spoken Dialogue Systems
In a Wizard-of-Oz experiment with multiple wizard subjects, each wizard viewed automated speech recognition (ASR) results for utterances whose interpretation is critical to task s...
Rebecca J. Passonneau, Susan L. Epstein, Tiziana L...
NAACL
2010
13 years 2 months ago
Automatic Evaluation of Topic Coherence
This paper introduces the novel task of topic coherence evaluation, whereby a set of words, as generated by a topic model, is rated for coherence or interpretability. We apply a r...
David Newman, Jey Han Lau, Karl Grieser, Timothy B...
NAACL
2010
13 years 2 months ago
Taxonomy Learning Using Word Sense Induction
Taxonomies are an important resource for a variety of Natural Language Processing (NLP) applications. Despite this, the current stateof-the-art methods in taxonomy learning have d...
Ioannis P. Klapaftis, Suresh Manandhar
NAACL
2010
13 years 2 months ago
Not All Seeds Are Equal: Measuring the Quality of Text Mining Seeds
Open-class semantic lexicon induction is of great interest for current knowledge harvesting algorithms. We propose a general framework that uses patterns in bootstrapping fashion ...
Zornitsa Kozareva, Eduard H. Hovy
NAACL
2010
13 years 2 months ago
Accurate Non-Hierarchical Phrase-Based Translation
A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend...
Michel Galley, Christopher D. Manning