337 citations · 699 across the 35 of their papers we have counts for
43 papers
Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages
Deevyanshu Malu, Deeptanshu Malu, Sunita Sarawagi
Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translation…
Towards Universal Calibration for In-Context Classification
Awik Dhar, Sunita Sarawagi, Arpit Agarwal
In-Context Learning (ICL) has received a lot of interest recently due to its ability to improve classification accuracy for new tasks without having to fine-tune the model over the…
Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs
Siddhesh Thombre, Manasi Patwardhan, Sunita Sarawagi
Integrating heterogeneous relational databases into a centralized ontology remains a persistent challenge in enterprise knowledge representation, primarily due to semantic heteroge…
Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing
Mayank Kothyari, Sunita Sarawagi, Soumen Chakrabarti +2
LLMs are increasingly used as seq2seq translators from natural language utterances to structured programs, a process called semantic interpretation. Unlike atomic labels or token s…
Efficient Training of Language Models with Compact and Consistent Next Token Distributions
Ashutosh Sathe, Sunita Sarawagi
Maximizing the likelihood of the next token is an established, statistically sound objective for pre-training language models. In this paper we show that we can train better models…
PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect
Lokesh Nagalapatti, Pranava Singhal, Avishek Ghosh +1
Given a dataset of individuals each described by a covariate vector, a treatment, and an observed outcome on the treatment, the goal of the individual treatment effect (ITE) estima…
Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing
Lokesh Nagalapatti, Akshay Iyer, Abir De +1
We address the Individualized continuous treatment effect (ICTE) estimation problem where we predict the effect of any continuous-valued treatment on an individual using observatio…
CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL
Mayank Kothyari, Dhruva Dhingra, Sunita Sarawagi +1
Existing Text-to-SQL generators require the entire schema to be encoded with the user text. This is expensive or impractical for large databases with tens of thousands of columns.…
Benchmarking and Improving Text-to-SQL Generation under Ambiguity
Adithya Bhaskar, Tushar Tomar, Ashutosh Sathe +1
Research in Text-to-SQL conversion has been largely benchmarked against datasets where each text query corresponds to one correct SQL. However, natural language queries over real-l…
Improving RNN-Transducers with Acoustic LookAhead
Vinit S. Unni, Ashish Mittal, Preethi Jyothi +1
RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical…
Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers
Abhijeet Awasthi, Soumen Chakrabarti, Sunita Sarawagi
Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bi…
Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers
Abhijeet Awasthi, Ashutosh Sathe, Sunita Sarawagi
Text-to-SQL parsers typically struggle with databases unseen during the train time. Adapting parsers to new databases is a challenging problem due to the lack of natural language q…
Bootstrapping Multilingual Semantic Parsers using Large Language Models
Abhijeet Awasthi, Nitish Gupta, Bidisha Samanta +3
Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remain…
Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding
Soumya Chatterjee, Sunita Sarawagi, Preethi Jyothi
Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded. Good online alignmen…
Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages
Vaidehi Patil, Partha Talukdar, Sunita Sarawagi
Pre-trained multilingual language models such as mBERT and XLM-R have demonstrated great potential for zero-shot cross-lingual transfer to low web-resource languages (LRL). However…
Adaptive Discounting of Implicit Language Models in RNN-Transducers
Vinit Unni, Shreya Khare, Ashish Mittal +3
RNN-Transducer (RNN-T) models have become synonymous with streaming end-to-end ASR systems. While they perform competitively on a number of evaluation categories, rare words pose a…
Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts
Prathamesh Deshpande, Sunita Sarawagi
Long range forecasts are the starting point of many decision support systems that need to draw inference from high-level aggregate patterns on forecasted values. State of the art t…
Focus on the Common Good: Group Distributional Robustness Follows
Vihari Piratla, Praneeth Netrapalli, Sunita Sarawagi
We consider the problem of training a classification model with group annotated training data. Recent work has established that, if there is distribution shift across different gro…
Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
Anshul Nasery, Soumyadeep Thakur, Vihari Piratla +2
In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the…
Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations
Vihari Piratla, Soumen Chakrabarty, Sunita Sarawagi
Our goal is to evaluate the accuracy of a black-box classification model, not as a single aggregate on a given test data distribution, but as a surface over a large number of combi…
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study
Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil +3
Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resou…
Deep Indexed Active Learning for Matching Heterogeneous Entity Representations
Arjit Jain, Sunita Sarawagi, Prithviraj Sen
Given two large lists of records, the task in entity resolution (ER) is to find the pairs from the Cartesian product of the lists that correspond to the same real world entity. Typ…
Error-driven Fixed-Budget ASR Personalization for Accented Speakers
Abhijeet Awasthi, Aman Kansal, Sunita Sarawagi +1
We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker-specific utterances. Given a speaker and an ASR model, we propose a…
Missing Value Imputation on Multidimensional Time Series
Parikshit Bansal, Prathamesh Deshpande, Sunita Sarawagi
We present DeepMVI, a deep learning method for missing value imputation in multidimensional time-series datasets. Missing values are commonplace in decision support platforms that…