Sunita Sarawagi's Lab at IIT Bombay
Team Projects PublicationsOur goal is to develop sytems for Text-to-Code generation, specifically Text-to-SQL, that are easy to customize to new schema, reliable, and efficient. A good overall pitch of our work (as of early 2024) can be found in these [slides]. For more recent work, please see our recent papers.
Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding. (Under review)
The Missing Alignment Link of In-context Learning on Sequences. Harshvardhan Agarwal, Sunita Sarawagi. In ICML 2025
Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing. Mayank Kothyari, Sunita Sarawagi, Soumen Chakrabarti, Gaurav Arora, Srujana Merugu. In NAACL 2025
Benchmarking and Improving Text-to-SQL Generation under Ambiguity. Adithya Bhaskar, Tushar Tomar, Ashutosh Sathe, Sunita Sarawagi In EMNLP 2023.
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL. Mayank Kothyari, Dhruva Dhingra, Sunita Sarawagi, and Soumen Chakrabarti In EMNLP 2023.
Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models. Harshit Varma, Abhijeet Awasthi and Sunita Sarawagi In ICML 2023.
In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations Ashish Mittal, Sunita Sarawagi, and Preethi Jyothi In ICLR 2023.
Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers Abhijeet Awasthi, Soumen Chakrabarti, and Sunita Sarawagi In AAAI 2023.
Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers Abhijeet Awasthi, Ashutosh Sathe and Sunita Sarawagi. In EMNLP (Long paper) 2022.