Fetching the paper…
Reading the bibliography…
Recent work has shown that LSTMs trained on a generic language modeling objective capture syntax-sensitive generalizations such as long-distance number agreement.
Long short-term memory
Sepp Hochreiter and Jürgen Schmidhuber. 1997 · 1997
Earlier work this paper cites.
On the biological plausibility of grandmother cells: Implications for neural network theories in psychology and neuroscience
Jeffrey Bowers. 2009 · 2009
Earlier work this paper cites.
Characterizing the dynamics of mental representations: The temporal generalization method
Jean-Rémi King and Stanislas Dehaene. 2014 · 2014
Earlier work this paper cites.
From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning
Lieke Gelderloos and Grzegorz Chrupała. 2016 · 2016
Earlier work this paper cites.
Visualizing and understanding recurrent networks
Andrej Karpathy, Justin Johnson, and Fei-Fei Li. 2016 · 2016
Earlier work this paper cites.
Visualizing and understanding neural models in NLP
Jiwei Li, Xinlei Chen, Eduard Hovy, and Dan Jurafsky. 2016 · 2016
Earlier work this paper cites.
Assessing the ability of LSTMs to learn syntax-sensitive dependencies
Tal Linzen, Emmanuel Dupoux, and Yoav Goldberg. 2016 · 2016
Earlier work this paper cites.
Fine-grained analysis of sentence embeddings using auxiliary prediction tasks
Yossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, and Yoav Goldberg. 2017 · 2017
Earlier work this paper cites.
Understanding intermediate layers using linear classifier probes
Guillaume Alain and Yoshua Bengio. 2017 · 2017
Cited alongside, same era.
Using deep neural networks to learn syntactic agreement
Jean-Philippe Bernardy and Shalom Lappin. 2017 · 2017
Cited alongside, same era.
Neurophysiological dynamics of phrase-structure building during sentence processing
Matthew Nelson, Imen El Karoui, Kristof Giber, Xiaofang Yang, Laurent Cohen, Hilda Koopman, Sydney Cash, Lionel Naccache, John Hale, Christophe Pallier, and Stanislas Dehaene. 2017 · 2017
Cited alongside, same era.
Learning to generate reviews and discovering sentiment
Alec Radford, Rafal Jozefowicz, and Ilya Sutskever. 2017 · 2017
Cited alongside, same era.
Memory visualization for gated recurrent neural networks in speech recognition
Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, and Shiyue Zhang. 2017 · 2017
Cited alongside, same era.
Visualisation and ’diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure
Dieuwke Hupkes, Sara Veldhoen, and Willem Zuidema. 2018 · 2018
Later among the works it cites.
Do language models understand anything? on the ability of lstms to understand negative polarity items
Jaap Jumelet and Dieuwke Hupkes. 2018 · 2018
Later among the works it cites.
‘Indicatements’ that character language models learn English morpho-syntactic units and regularities
Yova Kementchedjhieva and Adam Lopez. 2018 · 2018
Later among the works it cites.
Single neurons in the human brain encode numbers
Esther Kutter, Jan Bostroem, Christian Elger, Florian Mormann, and Andreas Nieder. 2018 · 2018
Later among the works it cites.
Distinct patterns of syntactic agreement errors in recurrent networks and humans
Tal Linzen and Brian Leonard. 2018 · 2018
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
RNN simulations of grammaticality judgments on long-distance dependencies
Shammur Chowdhury and Roberto Zamparelli. 2018 · 2018
Cited alongside, same era.
Under the hood: Using diagnostic classifiers to investigate and improve how language models track agreement information
Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes, and Willem Zuidema. 2018 · 2018
Cited alongside, same era.
Colorless green recurrent networks dream hierarchically
Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, and Marco Baroni. 2018 · 2018
Cited alongside, same era.
The perils of natural behavioral tests for unnatural models: The case of number agreement
Adhiguna Kuncoro, Chris Dyer, John Hale, and Phil Blunsom. 2018a
Cited in the paper.
LSTMs can learn syntax-sensitive dependencies well, but modeling structure makes them better
Adhiguna Kuncoro, Chris Dyer, John Hale, Dani Yogatama, Stephen Clark, and Phil Blunsom. 2018b
Cited in the paper.
Targeted syntactic evaluation of language models
Rebecca Marvin and Tal Linzen. 2018 · 2018
Later among the works it cites.
What do RNN language models learn about filler–gap dependencies?
Ethan Wilcox, Roger Levy, Takashi Morita, and Richard Futrell. 2018 · 2018
Later among the works it cites.