Gábor Melis's guest appearances

Gábor Melis

NLP Highlights

Sebastian Ruder

Ines Montani

Noah Smith

Michael Collins

Brendan O'Connor

Victor Sanh

Sam Bowman

Nathan Schneider

Matt Gardner

Chris Dyer

John Hewitt

Dan Roth

Leon Derczynski

Zhou Yu

Jon Clark

OwlTail

Recent arxiv paper by Gábor Melis, Chris Dyer, and Phil Blunsom.Gábor comes on the podcast to tell us about his work.  He performs a thorough comparison between vanilla LSTMs and recurrent highway networks on the language modeling task, showing that when both methods are given equal amounts of hyperparameter tuning, LSTMs perform better, in contrast to prior work claiming that recurrent highway networks perform better.  We talk about parameter tuning, training variance, language model evaluation, and other related issues.https://www.semanticscholar.org/paper/On-the-State-of-the-Art-of-Evaluation-in-Neural-La-Melis-Dyer/2397ce306e5d7f3d0492276e357fb1833536b5d8

Recent arxiv paper by Gábor Melis, Chris Dyer, and Phil Blunsom.<br><br>Gábor comes on the podcast to tell us about his work.  He performs a thorough comparison between vanilla LSTMs and recurrent highway networks on the language modeling task, showing that when both methods are given equal amounts of hyperparameter tuning, LSTMs perform better, in contrast to prior work claiming that recurrent highway networks perform better.  We talk about parameter tuning, training variance, language model evaluation, and other related issues.<br><br><a href="https://www.semanticscholar.org/paper/On-the-State-of-the-Art-of-Evaluation-in-Neural-La-Melis-Dyer/2397ce306e5d7f3d0492276e357fb1833536b5d8" rel="nofollow" target="_blank">https://www.semanticscholar.org/paper/On-the-State-of-the-Art-of-Evaluation-in-Neural-La-Melis-Dyer/2397ce306e5d7f3d0492276e357fb1833536b5d8</a>

40 - On the State of the Art of Evaluation in Neural Language Models, with Gábor Melis