no code implementations • ICON 2021 • Saujas Vaduguru, Partho Sarthi, Monojit Choudhury, Dipti Sharma
Learning linguistic generalizations from only a few examples is a challenging task.
no code implementations • 14 May 2024 • Akhila Yerukola, Saujas Vaduguru, Daniel Fried, Maarten Sap
Humans often express their communicative intents indirectly or non-literally, which requires their interlocutors -- human or AI -- to understand beyond the literal meaning of words.
1 code implementation • 9 Nov 2023 • Saujas Vaduguru, Daniel Fried, Yewen Pu
Programming-by-example is the task of synthesizing a program that is consistent with a set of user-provided input-output examples.
1 code implementation • 26 Oct 2023 • Justin T. Chiu, Wenting Zhao, Derek Chen, Saujas Vaduguru, Alexander M. Rush, Daniel Fried
Large language models (LLMs) excel at processing and generating both text and code.
1 code implementation • 1 Sep 2023 • Yewen Pu, Saujas Vaduguru, Priyan Vaithilingam, Elena Glassman, Daniel Fried
We prove that for a pragmatic synthesizer that uses a single demonstration, our global ranking method exactly replicates RSA's ranked responses.
no code implementations • 5 Apr 2022 • Saujas Vaduguru, Kevin Ellis, Yewen Pu
Surprisingly, we find that the synthesizer assuming a factored approximation performs better than a synthesizer assuming an exact joint distribution when evaluated on natural human inputs.
1 code implementation • ACL (SIGMORPHON) 2021 • Saujas Vaduguru, Aalok Sathe, Monojit Choudhury, Dipti Misra Sharma
Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples.