49 citations · 93 across the 11 of their papers we have counts for
14 papers
The Right Call for Software Benchmarking: Consistent Decisions in Stateful Environments
Gábor Melis
In the perpetual pursuit of performance, modern computing systems rely ever more on stateful mechanisms to accommodate the dynamics of workloads and physical environments, bolsteri…
Adaptive Hashing: Faster Hash Functions with Fewer Collisions
Gábor Melis
Hash tables are ubiquitous, and the choice of hash function, which maps a key to a bucket, is key to their performance. We argue that the predominant approach of fixing the hash fu…
Circling Back to Recurrent Models of Language
Gábor Melis
Just because some purely recurrent models suffer from being hard to optimize and inefficient on today's hardware, they are not necessarily bad models of language. We demonstrate th…
Two-Tailed Averaging: Anytime, Adaptive, Once-in-a-While Optimal Weight Averaging for Better Generalization
Gábor Melis
Tail Averaging improves on Polyak averaging's non-asymptotic behaviour by excluding a number of leading iterates of stochastic optimization from its calculations. In practice, with…
Mutual Information Constraints for Monte-Carlo Objectives
Gábor Melis, András György, Phil Blunsom
A common failure mode of density models trained as variational autoencoders is to model the data without relying on their latent variables, rendering these variables useless. Two c…
Capturing document context inside sentence-level neural machine translation models with self-training
Elman Mansimov, Gábor Melis, Lei Yu
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received l…
A Critical Analysis of Biased Parsers in Unsupervised Parsing
Chris Dyer, Gábor Melis, Phil Blunsom
A series of recent papers has used a parsing algorithm due to Shen et al. (2018) to recover phrase-structure trees based on proxies for "syntactic depth." These proxy depths are ob…
Unsupervised Recurrent Neural Network Grammars
Yoon Kim, Alexander M. Rush, Lei Yu +3
Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence i…
Variational Smoothing in Recurrent Neural Network Language Models
Lingpeng Kong, Gabor Melis, Wang Ling +2
We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017). We show that each variant of data noising is an instance of…
Encoding Spatial Relations from Natural Language
Tiago Ramalho, Tomáš Kočiský, Frederic Besse +5
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fa…
Pushing the bounds of dropout
Gábor Melis, Charles Blundell, Tomáš Kočiský +3
We show that dropout training is best understood as performing MAP estimation concurrently for a family of conditional models whose objectives are themselves lower bounded by the o…
The NarrativeQA Reading Comprehension Challenge
Tomáš Kočiský, Jonathan Schwarz, Phil Blunsom +4
Reading comprehension (RC)---in contrast to information retrieval---requires integrating information and reasoning about events, entities, and their relations across a full documen…
On the State of the Art of Evaluation in Neural Language Models
Gábor Melis, Chris Dyer, Phil Blunsom
Ongoing innovations in recurrent neural network architectures have provided a steady influx of apparently state-of-the-art results on language modelling benchmarks. However, these…
Semantic Parsing with Semi-Supervised Sequential Autoencoders
Tomáš Kočiský, Gábor Melis, Edward Grefenstette +4
We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent se…