S
Swabha Swayamdipta
Researcher at Allen Institute for Artificial Intelligence
Publications - 48
Citations - 5098
Swabha Swayamdipta is an academic researcher from Allen Institute for Artificial Intelligence. The author has contributed to research in topics: Parsing & Semantics. The author has an hindex of 19, co-authored 48 publications receiving 3279 citations. Previous affiliations of Swabha Swayamdipta include Carnegie Mellon University & Columbia University.
Papers
More filters
Proceedings ArticleDOI
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
Suchin Gururangan,Ana Marasović,Ana Marasović,Swabha Swayamdipta,Kyle Lo,Iz Beltagy,Doug Downey,Noah A. Smith,Noah A. Smith +8 more
TL;DR: It is consistently found that multi-phase adaptive pretraining offers large gains in task performance, and it is shown that adapting to a task corpus augmented using simple data selection strategies is an effective alternative, especially when resources for domain-adaptive pretraining might be unavailable.
Proceedings ArticleDOI
Annotation Artifacts in Natural Language Inference Data
Suchin Gururangan,Swabha Swayamdipta,Omer Levy,Roy Schwartz,Roy Schwartz,Samuel R. Bowman,Noah A. Smith +6 more
TL;DR: The authors showed that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI and 53% of MultiNLI, showing that specific linguistic phenomena such as negation and vagueness are highly correlated with certain inference classes.
Posted Content
DyNet: The Dynamic Neural Network Toolkit
Graham Neubig,Chris Dyer,Yoav Goldberg,Austin Matthews,Waleed Ammar,Antonios Anastasopoulos,Miguel Ballesteros,David Chiang,Daniel Clothiaux,Trevor Cohn,Kevin Duh,Manaal Faruqui,Cynthia Gan,Dan Garrette,Yangfeng Ji,Lingpeng Kong,Adhiguna Kuncoro,Gaurav Kumar,Chaitanya Malaviya,Paul Michel,Yusuke Oda,Matthew Richardson,Naomi Saphra,Swabha Swayamdipta,Pengcheng Yin +24 more
TL;DR: DyNet is a toolkit for implementing neural network models based on dynamic declaration of network structure that has an optimized C++ backend and lightweight graph representation and is designed to allow users to implement their models in a way that is idiomatic in their preferred programming language.
Posted Content
Annotation Artifacts in Natural Language Inference Data
Suchin Gururangan,Swabha Swayamdipta,Omer Levy,Roy Schwartz,Roy Schwartz,Samuel R. Bowman,Noah A. Smith +6 more
TL;DR: It is shown that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI and 53% of MultiNLI, and that specific linguistic phenomena such as negation and vagueness are highly correlated with certain inference classes.
Proceedings ArticleDOI
Transfer Learning in Natural Language Processing.
TL;DR: Transfer learning as discussed by the authors is a set of methods that extend the classical supervised machine learning paradigm by leveraging data from additional domains or tasks to train a model with better generalization properties, which can be used for NLP tasks.