Papers by Prasann Singhal

2 papers
Assessing Out-of-Domain Language Model Performance from Few Examples (2023.eacl-main)

Copied to clipboard

Challenge: Pretrained language models exhibit impressive generalization capabilities, but behave unpredictably under certain domain shifts.
Approach: They propose to incorporate attributions into a few-shot model predicting out-of-domain (OOD) performance task to find out if models agree with pathological heuristics that may indicate worse generalization capabilities.
Outcome: The proposed model-based model-learning model can perform better on a few-shot example set, and incorporate feature attributions to improve it.
EEL: Efficiently Encoding Lattices for Reranking (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for decoding conditional text are slow to apply to large numbers of hypotheses.
Approach: They propose a method that can efficiently encode lattices of generated outputs using Transformers.
Outcome: The proposed method can extract high-quality hypotheses from lattices with minimal degradation error compared to naive reranking methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations