no code implementations • 24 Apr 2024 • Jiaqing Yuan, Lin Pan, Chung-Wei Hang, Jiang Guo, Jiarong Jiang, Bonan Min, Patrick Ng, Zhiguo Wang
By further decoupling model known and unknown knowledge, we find the degradation is attributed to exemplars that contradict a model's known knowledge, as well as the number of such exemplars.
no code implementations • 5 Jun 2023 • Jiaqing Yuan, Michele Merler, Mihir Choudhury, Raju Pavuluri, Munindar P. Singh, Maja Vukovic
Entity standardization maps noisy mentions from free-form text to standard entities in a knowledge base.
no code implementations • 20 Mar 2023 • Jiaqing Yuan, Munindar P. Singh
We propose a domain-adaptive pretraining objective to integrate conversational structure information and a multitask learning scheme to leverage the distance from each utterance to derailment.
no code implementations • 19 Mar 2023 • Vaibhav Garg, Jiaqing Yuan, Rujie Xi, Munindar P. Singh
We develop a natural language-based model to identify sentences from a post that describe any of the above three categories.