1 code implementation • 16 Nov 2023 • Shivanshu Gupta, Clemens Rosenbaum, Ethan R. Elenberg
Further, we experiment with two variations: (1) fine-tuning gist models for each dataset and (2) multi-task training a single model on a large collection of datasets.
1 code implementation • 16 Nov 2023 • Ben Bogin, Shivanshu Gupta, Peter Clark, Ashish Sabharwal
In-context learning (ICL) is an appealing approach for semantic parsing due to its few-shot nature and improved generalization.
no code implementations • 25 May 2023 • Shivanshu Gupta, Yoshitomo Matsubara, Ankit Chadha, Alessandro Moschitti
While impressive performance has been achieved on the task of Answer Sentence Selection (AS2) for English, the same does not hold for languages that lack large labeled datasets.
1 code implementation • 24 May 2023 • Shivanshu Gupta, Matt Gardner, Sameer Singh
In-context learning (ICL), the ability of large language models to perform novel tasks by conditioning on a prompt with a few task examples, requires these examples to be informative about the test instance.
no code implementations • 8 Dec 2022 • Dheeru Dua, Shivanshu Gupta, Sameer Singh, Matt Gardner
The intermediate supervision is typically manually written, which can be expensive to collect.
1 code implementation • 16 Mar 2022 • Shivanshu Gupta, Sameer Singh, Matt Gardner
A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches.
1 code implementation • 15 Jan 2022 • Ben Bogin, Shivanshu Gupta, Jonathan Berant
While recent work has convincingly showed that sequence-to-sequence models struggle to generalize to new compositions (termed compositional generalization), little is known on what makes compositional generalization hard on a particular test instance.
1 code implementation • EMNLP 2021 • Ben Bogin, Shivanshu Gupta, Matt Gardner, Jonathan Berant
Due to the automatic generation process, COVR facilitates the creation of compositional splits, where models at test time need to generalize to new concepts and compositions in a zero- or few-shot setting.