Search Results for author:
Found 6 papers, 0 papers with code
LLMs-augmented Contextual Bandit
Contextual bandits have emerged as a cornerstone in reinforcement learning, enabling systems to make decisions with partial feedback.
Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users
We make available a pairing of word embeddings and their human-annotated importance scores.
Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues
Word error rate, a traditional metric for evaluating automatic speech recognition, fails to capture that some words are more important for a system to transcribe correctly than others.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
SNAG: Spoken Narratives and Gaze Dataset
Humans rely on multiple sensory modalities when examining and reasoning over images.
