research
∙
05/25/2022
Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
Instruction tuning is an emergent paradigm in NLP wherein natural langua...
share
research
∙
03/18/2022
Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges
This is a report on the NSF Future Directions Workshop on Automatic Eval...
research
∙
10/15/2021
Breaking Down Multilingual Machine Translation
While multilingual training is now an essential ingredient in machine tr...
research
∙
10/12/2021
Are you doing what I say? On modalities alignment in ALFRED
ALFRED is a recently proposed benchmark that requires a model to complet...
research
∙
09/29/2021
Improving Dialogue State Tracking by Joint Slot Modeling
Dialogue state tracking models play an important role in a task-oriented...
research
∙
06/07/2021
A Comprehensive Assessment of Dialog Evaluation Metrics
Automatic evaluation metrics are a crucial component of dialog systems r...
research
∙
08/31/2019
QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization
Standard accuracy metrics indicate that modern reading comprehension sys...
research
∙
08/14/2019
FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
Conversational machine comprehension requires deep understanding of the ...
research
∙
08/14/2019
Reactive Multi-Stage Feature Fusion for Multimodal Dialogue Modeling
Visual question answering and visual dialogue tasks have been increasing...
research
∙
08/08/2018