Gábor Melis

According to our database1, Gábor Melis authored at least 16 papers between 2014 and 2022.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2022
Mutual Information Constraints for Monte-Carlo Objectives to Prevent Posterior Collapse Especially in Language Modelling.
J. Mach. Learn. Res., 2022

Circling Back to Recurrent Models of Language.
CoRR, 2022

Two-Tailed Averaging: Anytime Adaptive Once-in-a-while Optimal Iterate Averaging for Stochastic Optimization.
CoRR, 2022

2020
Mutual Information Constraints for Monte-Carlo Objectives.
CoRR, 2020

Capturing document context inside sentence-level neural machine translation models with self-training.
CoRR, 2020

Mogrifier LSTM.
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
A Critical Analysis of Biased Parsers in Unsupervised Parsing.
CoRR, 2019

Unsupervised Recurrent Neural Network Grammars.
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019

Variational Smoothing in Recurrent Neural Network Language Models.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
The NarrativeQA Reading Comprehension Challenge.
Trans. Assoc. Comput. Linguistics, 2018

Encoding Spatial Relations from Natural Language.
CoRR, 2018

Pushing the bounds of dropout.
CoRR, 2018

Memory Architectures in Recurrent Neural Network Language Models.
Proceedings of the 6th International Conference on Learning Representations, 2018

On the State of the Art of Evaluation in Neural Language Models.
Proceedings of the 6th International Conference on Learning Representations, 2018

2016
Semantic Parsing with Semi-Supervised Sequential Autoencoders.
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016

2014
Dissecting the Winning Solution of the HiggsML Challenge.
Proceedings of the Workshop on High-energy Physics and Machine Learning, 2014


  Loading...