Mukund Sridhar

Instilling Type Knowledge in Language Models via Multi-Task QA

Julian McAuley, W. Hamza, Shuyang Li, 2022, NAACL-HLT.

Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems

Dilek Z. Hakkani-Tür, Jack G. M. FitzGerald, Claudio Delli Bovi, 2022, KDD.

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

Jack G. M. FitzGerald, Stephen Rawls, Anna Rumshisky, 2022, ArXiv.

Zero-shot Generalization in Dialog State Tracking through Generative Question Answering

Shang-Wen Li, Jin Cao, Wael Hamza, 2021, EACL.

Towards Realistic Single-Task Continuous Learning Research for NER

Anil Ramakrishna, He Xie, Yuval Merhav, 2021, EMNLP.

Advin: Automatically Discovering Novel Domains and Intents from User Text Utterances

Mukund Sridhar, Rahul Gupta, Shankar Ananthakrishnan, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automatic Discovery of Novel Intents & Domains from Text Utterances pdf

Rahul Gupta, Aman Alok, Nikhita Vedula, 2020, ArXiv.

An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing

Nicolas Guenon des Mesnards, Aoxiao Zhong, S. Movaghati, 2023, ACL.

Low-Resource Compositional Semantic Parsing with Concept Pretraining

A. McCallum, Konstantine Arkoudas, Subendhu Rongali, 2023, EACL.