The narrativeqa reading comprehension challenge T Kočiský, J Schwarz, P Blunsom, C Dyer, KM Hermann, G Melis, ... Transactions of the Association for Computational Linguistics 6, 317-328, 2018 | 633 | 2018 |
On the State of the Art of Evaluation in Neural Language Models G Melis, C Dyer, P Blunsom arXiv preprint arXiv:1707.05589, 2017 | 616 | 2017 |
Unsupervised Recurrent Neural Network Grammars Y Kim, AM Rush, L Yu, A Kuncoro, C Dyer, G Melis arXiv preprint arXiv:1904.03746, 2019 | 144 | 2019 |
Mogrifier LSTM G Melis, T Kočiský, P Blunsom arXiv preprint arXiv:1909.01792, 2019 | 143 | 2019 |
Semantic parsing with semi-supervised sequential autoencoders T Kočiský, G Melis, E Grefenstette, C Dyer, W Ling, P Blunsom, ... arXiv preprint arXiv:1609.09315, 2016 | 97 | 2016 |
Variational Smoothing in Recurrent Neural Network Language Models L Kong, G Melis, W Ling, L Yu, D Yogatama arXiv preprint arXiv:1901.09296, 2019 | 80* | 2019 |
Memory Architectures in Recurrent Neural Network Language Models D Yogatama, Y Miao, G Melis, W Ling, A Kuncoro, C Dyer, P Blunsom Proc. ICLR, 2018 | 61 | 2018 |
A Critical Analysis of Biased Parsers in Unsupervised Parsing C Dyer, G Melis, P Blunsom arXiv preprint arXiv:1909.09428, 2019 | 25 | 2019 |
Encoding spatial relations from natural language T Ramalho, T Kočiský, F Besse, SM Eslami, G Melis, F Viola, P Blunsom, ... arXiv preprint arXiv:1807.01670, 2018 | 17* | 2018 |
Pushing the bounds of dropout G Melis, C Blundell, T Kočiský, KM Hermann, C Dyer, P Blunsom arXiv preprint arXiv:1805.09208, 2018 | 15 | 2018 |
Six wins Hex tournament G Melis, R Hayward ICGA JOURNAL 26 (4), 277-280, 2003 | 15 | 2003 |
Capturing document context inside sentence-level neural machine translation models with self-training E Mansimov, G Melis, L Yu arXiv preprint arXiv:2003.05259, 2020 | 14 | 2020 |
Dissecting the winning solution of the higgsml challenge G Melis NIPS 2014 Workshop on High-energy Physics and Machine Learning, 57-67, 2015 | 14 | 2015 |
Hex Gold at Graz: Six Defeats Mongoose G Melis, R Hayward to appear ICGA Journal, 2003 | 4 | 2003 |
Circling Back to Recurrent Models of Language G Melis arXiv preprint arXiv:2211.01848, 2022 | 2 | 2022 |
Mutual Information Constraints for Monte-Carlo Objectives to Prevent Posterior Collapse Especially in Language Modelling G Melis, A György, P Blunsom Journal of Machine Learning Research 23 (75), 1-36, 2022 | 2 | 2022 |
Towards Better Generative Models of Language G Melis UCL (University College London), 2024 | | 2024 |
Two-Tailed Averaging: Anytime, Adaptive, Once-in-a-While Optimal Weight Averaging for Better Generalization G Melis arXiv preprint arXiv:2209.12581, 2022 | | 2022 |