-
Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
Most available semantic parsing datasets, comprising of pairs of natural...
06/09/2021 ∙ by Moshe Hazoom, et al. ∙
0
∙
share
read it
-
MedICaT: A Dataset of Medical Images, Captions, and Textual References
Understanding the relationship between figures and text is key to scient...
10/12/2020 ∙ by Sanjay Subramanian, et al. ∙
18
∙
share
read it
-
Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
Answering questions that involve multi-step reasoning requires decomposi...
07/01/2020 ∙ by Ben Bogin, et al. ∙
7
∙
share
read it
-
Obtaining Faithful Interpretations from Compositional Neural Networks
Neural module networks (NMNs) are a popular approach for modeling compos...
05/02/2020 ∙ by Sanjay Subramanian, et al. ∙
22
∙
share
read it
-
Evaluating NLP Models via Contrast Sets
Standard test sets for supervised learning evaluate in-distribution gene...
04/06/2020 ∙ by Matt Gardner, et al. ∙
0
∙
share
read it
-
Global Reasoning over Database Structures for Text-to-SQL Parsing
State-of-the-art semantic parsers rely on auto-regressive decoding, emit...
08/29/2019 ∙ by Ben Bogin, et al. ∙
0
∙
share
read it
-
Grammar-based Neural Text-to-SQL Generation
The sequence-to-sequence paradigm employed by neural text-to-SQL models ...
05/30/2019 ∙ by Kevin Lin, et al. ∙
0
∙
share
read it
-
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
Research on parsing language to SQL has largely ignored the structure of...
05/15/2019 ∙ by Ben Bogin, et al. ∙
0
∙
share
read it
-
Emergence of Communication in an Interactive World with Consistent Speakers
Training agents to communicate with one another given task-based supervi...
09/03/2018 ∙ by Ben Bogin, et al. ∙
0
∙
share
read it
-
Language Generation with Recurrent Generative Adversarial Networks without Pre-training
Generative Adversarial Networks (GANs) have shown great promise recently...
06/05/2017 ∙ by Ofir Press, et al. ∙
0
∙
share
read it
