117 citations · 488 across the 32 of their papers we have counts for
7 papers · 1 filter
Exploring Strategies for Modeling Sign Language Phonology
Lee Kezar, Riley Carlin, Tejas Srinivasan +3
Like speech, signs are composed of discrete, recombinable features called phonemes. Prior work shows that models which can recognize phonemes are better at sign recognition, motiva…
Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering
Wang Zhu, Jesse Thomason, Robin Jia
We train a language model (LM) to robustly answer multistep questions by generating and answering sub-questions. We propose Chain-of-Questions, a framework that trains a model to g…
I2I: Initializing Adapters with Improvised Knowledge
Tejas Srinivasan, Furong Jia, Mohammad Rostami +1
Adapters present a promising solution to the catastrophic forgetting problem in continual learning. However, training independent Adapter modules for every new task misses an oppor…
Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation
Yuliang Cai, Jesse Thomason, Mohammad Rostami
The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Contin…
Improving Sign Recognition with Phonology
Lee Kezar, Jesse Thomason, Zed Sevcikova Sehyr
We use insights from research on American Sign Language (ASL) phonology to train models for isolated sign language recognition (ISLR), a step towards automatic sign language unders…
Multimodal Speech Recognition for Language-Guided Embodied Agents
Allen Chang, Xiaoyuan Zhu, Aarav Monga +3
Benchmarks for language-guided embodied agents typically assume text-based instructions, but deployed agents will encounter spoken instructions. While Automatic Speech Recognition…