57 citations · 110 across the 10 of their papers we have counts for
11 papers
Syntax-Aware Language Modeling with Recurrent Neural Networks
Duncan Blythe, Alan Akbik, Roland Vollgraf
Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic si…
Causal Learning via Manifold Regularization
Steven M. Hill, Chris. J. Oates, Duncan A. Blythe +1
This paper frames causal structure estimation as a machine learning task. The idea is to treat indicators of causal relationships between variables as `labels' and to exploit avail…
Prediction and Quantification of Individual Athletic Performance
Duncan A. J. Blythe, Franz J. Király
We provide scientific foundations for athletic performance prediction on an individual level, exposing the phenomenology of individual athletic running performance in the form of a…
Meta-universality classes at criticality
Duncan A. J. Blythe, Vadim V. Nikulin
Inferring the presence of critical dynamics from continuous measure- ments is a challenging problem. We solve this problem by showing that continuous narrowband dynamics from a cri…
Algebraic-Combinatorial Methods for Low-Rank Matrix Completion with Application to Athletic Performance Prediction
Duncan A. J. Blythe, Louis Theran, Franz Kiraly
This paper presents novel algorithms which exploit the intrinsic algebraic and combinatorial structure of the matrix completion task for estimating missing en- tries in the general…
A rigorous and efficient asymptotic test for power-law cross-correlation
Duncan A. J. Blythe
Podobnik and Stanley recently proposed a novel framework, Detrended Cross-Correlation Analysis, for the analysis of power-law cross-correlation between two time-series, a phenomeno…