| BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation. | 0 | 0.34 | 2022 |
| SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark. | 0 | 0.34 | 2021 |
| Grounded Adaptation for Zero-shot Executable Semantic Parsing. | 0 | 0.34 | 2020 |
| Pre-training via Paraphrasing | 0 | 0.34 | 2020 |
| Simple Recurrent Units for Highly Parallelizable Recurrence. | 16 | 0.88 | 2018 |
| Data Noising as Smoothing in Neural Network Language Models. | 13 | 0.61 | 2017 |
| Naturalizing A Programming Language Via Interactive Learning | 8 | 0.53 | 2017 |
| Learning Language Games Through Interaction | 29 | 1.21 | 2016 |
| Estimating Mixture Models via Mixtures of Polynomials. | 0 | 0.34 | 2016 |
| Altitude Training: Strong Bounds for Single-Layer Dropout. | 11 | 0.62 | 2014 |
| Human Effort and Machine Learnability in Computer Aided Translation. | 13 | 0.59 | 2014 |
| A sub-constant improvement in approximating the positive semidefinite Grothendieck problem. | 0 | 0.34 | 2014 |
| Relaxations for inference in restricted Boltzmann machines. | 0 | 0.34 | 2014 |
| Simple MAP Inference via Low-Rank Relaxations. | 4 | 0.41 | 2014 |
| Feature Noising for Log-Linear Structured Prediction. | 11 | 1.03 | 2013 |
| Feature-Rich Phrase-based Translation: Stanford University's Submission to the WMT 2013 Translation Task | 3 | 0.42 | 2013 |
| Fast dropout training. | 26 | 8.42 | 2013 |
| Fast and Adaptive Online Training of Feature-Rich Translation Models. | 20 | 0.79 | 2013 |
| Feature-Rich Phrase-based Translation: Stanford University's Submission to the WMT 2013 Translation Task. | 0 | 0.34 | 2013 |
| Dropout Training as Adaptive Regularization. | 114 | 9.49 | 2013 |
| Relaxations for inference in restricted Boltzmann machines. | 3 | 0.41 | 2013 |
| Baselines and bigrams: simple, good sentiment and topic classification | 196 | 9.06 | 2012 |
| Transforming auto-encoders | 74 | 7.46 | 2011 |
