960 citations · 3.4k across the 60 of their papers we have counts for
5 papers · 1 filter
Quantifying the Task-Specific Information in Text-Based Classifications
Zining Zhu, Aparna Balagopalan, Marzyeh Ghassemi +1
Recently, neural natural language models have attained state-of-the-art performance on a wide variety of tasks, but the high performance can result from superficial, surface-level…
Improving Dialogue Breakdown Detection with Semi-Supervised Learning
Nathan Ng, Marzyeh Ghassemi, Narendran Thangarajan +2
Building user trust in dialogue agents requires smooth and consistent dialogue exchanges. However, agents can easily lose conversational context and generate irrelevant utterances.…
Multiple Sclerosis Severity Classification From Clinical Text
Alister D Costa, Stefan Denkovski, Michal Malyska +5
Multiple Sclerosis (MS) is a chronic, inflammatory and degenerative neurological disease, which is monitored by a specialist using the Expanded Disability Status Scale (EDSS) and r…
SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
Nathan Ng, Kyunghyun Cho, Marzyeh Ghassemi
Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve…
Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
Haoran Zhang, Amy X. Lu, Mohamed Abdalla +2
In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance…