252 citations
- Yahoo (United States)US11 papers
- Yahoo (Spain)ES8 papers
- Telefonica Research and DevelopmentES7 papers
- IBM (United States)US4 papers
- University of CambridgeGB4 papers
- Cornell UniversityUS3 papers
- Johns Hopkins UniversityUS3 papers
- Microsoft (United States)US3 papers
- University of ChicagoUS3 papers
- Columbia UniversityUS2 papers
- Georgia Institute of TechnologyUS2 papers
- Google (United States)US2 papers
13 papers · 1 filter
There's No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction
Courtney Napoles, Keisuke Sakaguchi, Joel Tetreault
Current methods for automatically evaluating grammatical error correction (GEC) systems rely on gold-standard references. However, these methods suffer from penalizing grammatical…
Improved Strongly Adaptive Online Learning using Coin Betting
Kwang-Sung Jun, Francesco Orabona, Rebecca Willett +1
This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a st…
Deep Architectures for Face Attributes
Tobi Baumgartner, Jack Culpepper
We train a deep convolutional neural network to perform identity classification using a new dataset of public figures annotated with age, gender, ethnicity and emotion labels, and…
On Locally Symmetric -Dimensional Riemannian Lie Groups
Nimpa Pefoukeu Romain, Wouafo Kamga Jean, Djiadeu Ngaha Michel Bertrand
In this paper, we use the powerful tool Milnor bases to classify all the dimensional connected and locally symmetric Riemannian Lie Groups by solving system of polynomial equat…
Multilingual Visual Sentiment Concept Matching
Nikolaos Pappas, Miriam Redi, Mercan Topkara +4
The impact of culture in visual emotion perception has recently captured the attention of multimedia research. In this study, we pro- vide powerful computational linguistics tools…
Distributed Flexible Nonlinear Tensor Factorization
Shandian Zhe, Kai Zhang, Pengyuan Wang +4
Tensor factorization is a powerful tool to analyse multi-way data. Compared with traditional multi-linear methods, nonlinear tensor factorization models are capable of capturing mo…