D
Dan Jurafsky
Researcher at Stanford University
Publications - 348
Citations - 50756
Dan Jurafsky is an academic researcher from Stanford University. The author has contributed to research in topics: Language model & Parsing. The author has an hindex of 93, co-authored 344 publications receiving 44536 citations. Previous affiliations of Dan Jurafsky include Carnegie Mellon University & University of Colorado Boulder.
Papers
More filters
Proceedings ArticleDOI
Textual entailment features for machine translation evaluation
TL;DR: Two regression models for the prediction of pairwise preference judgments among MT hypotheses are presented, based on feature sets that are motivated by textual entailment and incorporate lexical similarity as well as local syntactic features and specific semantic phenomena.
Type underspecification and On-line Type Construction in the Lexicon
Jean-Pierre Koenig,Dan Jurafsky +1 more
TL;DR: On-line type construction can advantageously replace mechanisms like lexical rules which are used in HPSG to model lexical productivity, and is directly applicable to any typed theory such as H PSG.
Proceedings Article
JESC: Japanese-English Subtitle Corpus
TL;DR: The Japanese-English Subtitle Corpus (JESC) as discussed by the authors is a large parallel corpus covering the underrepresented domain of conversational dialogue that consists of more than 3.2 million examples.
Proceedings ArticleDOI
The effect of language model probability on pronunciation reduction
TL;DR: It is shown that words which have a high unigram, bigram, or reverse bigram (given the following word) probability are shorter, more likely to have a reduced vowel, and more likelyto have a deleted final t or d.
Proceedings Article
Lateen EM: Unsupervised Training with Multiple Objectives, Applied to Dependency Grammar Induction
TL;DR: New training methods that aim to mitigate local optima and slow convergence in unsupervised training by using additional imperfect objectives, including lateen EM, showed that lateen strategies significantly speed up training of both EM algorithms, and improve accuracy for hard EM.