no code implementations • NAACL 2022 • Atijit Anuchitanukul, Julia Ive
The performance of Reinforcement Learning (RL) for natural language tasks including Machine Translation (MT) is crucially dependent on the reward formulation.
1 code implementation • 24 Jun 2022 • Atijit Anuchitanukul, Lucia Specia
We present Burst2Vec, our multi-task learning approach to predict emotion, age, and origin (i. e., native country/language) from vocal bursts.
no code implementations • 24 Nov 2021 • Atijit Anuchitanukul, Julia Ive, Lucia Specia
We then propose to bring these findings into computational detection models by introducing and evaluating (a) neural architectures for contextual toxicity detection that are aware of the conversational structure, and (b) data augmentation strategies that can help model contextual toxicity detection.
Ranked #1 on Toxic Comment Classification on CAD