Demo Data from VLDB 2026 / reviewers in the wild / expert
Jason Smith 0006
dblp:02/1964-6 · also Jason R. Smith 0001
· DBLP profile ↗
6ranked-venue papers
3as first author
0since 2021 · last 2013
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 5 · 3 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
2 papers |
Machine translation · 56% Deep learning architectures and training · 28% Information extraction and text analysis · 17% |
Topics — the 2 heaviest of 4, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Deep learning architectures and training › sequence modeling › sequence generation
sequence transduction |
0.1 | 1 | 2008 | Latent-Variable Modeling of String Transductions with Finite-State Methods · EMNLP 2008 |
Natural language and speech › Information extraction and text analysis › text mining
web text mining |
0.0 | 1 | 2013 | Dirt Cheap Web-Scale Parallel Text from the Common Crawl · ACL (1) 2013 |
Methods — techniques the papers use, named apart from their topics
bitext mining · 0.2latent variable modeling · 0.1finite-state methods · 0.1
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2013 | Dirt Cheap Web-Scale Parallel Text from the Common Crawl
Jason Smith 0006, Herve Saint-Amand, Magdalena Plamada, Philipp Koehn, Chris Callison-Burch, Adam Lopez |
ACL (1) | 1 |
| 2012 | Unsupervised Learning on an Approximate Corpus
Jason Smith 0006, Jason Eisner |
HLT-NAACL | 1 |
| 2010 | Hypothesis ranking and two-pass approaches for machine translation system combinationabstractGiven a number of machine translations of a source segment, the goal of system combination is to produce a new translation that has better quality than all of them. This paper describes a number of improvements that were recently added to the JHU system combination scheme: (i) A hypothesis ranking technique which orders the system outputs, on a per-segment basis, according to predicted translation quality, thus improving a subsequent incremental combination step. (ii) A two-pass combination procedure, which first produces several combination outputs with the given translations, and then performs one more combination step with these new outputs. Results from the NIST MT09 informal system combination evaluation on Arabic-to-English and Urdu-to-English1show that both approaches offer significant BLEU and TER gains over a baseline JHU combination scheme. Damianos Karakos, Jason Smith 0006, Sanjeev Khudanpur |
ICASSP | 2 |
| 2010 | Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment
Jason Smith 0006, Chris Quirk, Kristina Toutanova |
HLT-NAACL | 1 |
| 2008 | Latent-Variable Modeling of String Transductions with Finite-State Methods
Markus Dreyer, Jason Smith 0006, Jason Eisner |
EMNLP | 2 |
| 2008 | BART: A modular toolkit for coreference resolution
Yannick Versley, Simone Paolo Ponzetto, Massimo Poesio, Vladimir Eidelman, Alan Jern, Jason Smith 0006, Alessandro Moschitti |
LREC | 6 |