Papers by Saket Maheshwary

2 papers
A Strong Baseline for Query Efficient Attacks in a Black Box Setting (2021.emnlp-main)

Copied to clipboard

Challenge: Existing black box search methods are inefficient as they do not consider the amount of queries required to generate adversarial attacks.
Approach: They propose a query efficient attack strategy to generate plausible adversarial examples on text classification and entailment tasks.
Outcome: The proposed attack reduces query count by 75% across all datasets and target models compared to prior attacks in a limited query setting.
Pretraining and Finetuning Language Models on Geospatial Networks for Accurate Address Matching (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to address matching and building authoritative address catalogues are limited in data quality and require labeling effort to develop accurate models.
Approach: They propose to view addresses as an address graph and curate inputs by placing geospatially linked addresses in the same context.
Outcome: The proposed framework improves address matching and fine-tuning language models.

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