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
Knowledge-free induction of morphology using latent semantic analysis
Patrick Schone,Dan Jurafsky +1 more
TL;DR: A semantics-only algorithm for learning morphology which only proposes affixes when the stem and stem-plus-affix are sufficiently similar semantically and it is shown that this approach provides morphology induction results that rival a current state-of-the-art system.
Proceedings ArticleDOI
Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context
TL;DR: The authors investigated the role of context in an LSTM LM, through ablation studies, and found that the model is capable of using about 200 tokens of context on average, but sharply distinguishes nearby context (recent 50 tokens) from the distant history.
Proceedings Article
Automatic Extraction of Opinion Propositions and their Holders
TL;DR: An extension of semantic parsing techniques, coupled with additional lexical and syntactic features, that can produce labels for propositional opinions as opposed to other syntactic constituents is proposed.
Proceedings ArticleDOI
How Good Are Humans at Solving CAPTCHAs? A Large Scale Evaluation
TL;DR: In this paper, a large scale evaluation of captchas from the human perspective is presented, with the goal of assessing how much friction CAPTCHAs present to the average user.
How good are humans at solving captchas a large scale evaluation
TL;DR: Evidence from a week’s worth of eBay captchas suggests that the solving accuracies found in the study are close to real-world values, and that improving audioCaptchas should become a priority, as nearly 1% of all captchAs are delivered as audio rather than images.