NYU Linguistics department members (and recent alumni) will present the following papers at the Association for Computational Linguistics annual conference next month:
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, and Samuel R. Bowman
How Can We Accelerate Progress Towards Human-like Linguistic Generalization?
Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition
Paloma Jeretic, Alex Warstadt, Suvrat Bhooshan and Adina Williams
Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs
Michael Lepori, Tal Linzen and R. Thomas McCoy
Syntactic Data Augmentation Increases Robustness to Inference Heuristics
Junghyun Min, R. Thomas McCoy, Dipanjan Das, Emily Pitler and Tal Linzen
A Tale of a Probe and a Parser
Rowan Hall Maudslay, Josef Valvoda, Tiago Pimentel, Adina Williams and Ryan Cotterell
Adversarial NLI: A New Benchmark for Natural Language Understanding
Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston and Douwe Kiela
Information-Theoretic Probing for Linguistic Structure
Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams and Ryan Cotterell
Predicting Declension Class from Form and Meaning
Adina Williams, Tiago Pimentel, Arya D. McCarthy, Hagen Blix, Eleanor Chodroff and Ryan Cotterell
jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
Yada Pruksachatkun, Phil Yeres, Haokun Liu, Jason Phang, Phu Mon Htut, Alex Wang, Ian Tenney and Samuel R. Bowman (system demonstration paper)
Self-Training for Unsupervised Parsing with PRPN
Anhad Mohananey, Katharina Kann and Samuel R. Bowman (at the co-located International Conference on Parsing Technologies)
In addition to the papers above, NYU Data Science postdoc Clara Vania will give a keynote presentation at the co-located SIGMORPHON computational morphology, phonology, and former NYU Data Science postdoc Katharina Kann will organize a shared-task competition at the same event.