activity
20192021
most citedIntermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?

53 citations · 63 across the 3 of their papers we have counts for

collaborators

9 papers

cs.CL2021

Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers

Jason Phang, Haokun Liu, Samuel R. Bowman

Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly understood how neural networ…

cs.CL2021

Comparing Test Sets with Item Response Theory

Clara Vania, Phu Mon Htut, William Huang +6

Recent years have seen numerous NLP datasets introduced to evaluate the performance of fine-tuned models on natural language understanding tasks. Recent results from large pretrain…

cs.CL2020

Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually)

Alex Warstadt, Yian Zhang, Haau-Sing Li +2

One reason pretraining on self-supervised linguistic tasks is effective is that it teaches models features that are helpful for language understanding. However, we want pretrained…

cs.CL2020

Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data

William Huang, Haokun Liu, Samuel R. Bowman

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdwor…

cs.CL2020

Precise Task Formalization Matters in Winograd Schema Evaluations

Haokun Liu, William Huang, Dhara A. Mungra +1

Performance on the Winograd Schema Challenge (WSC), a respected English commonsense reasoning benchmark, recently rocketed from chance accuracy to 89% on the SuperGLUE leaderboard,…

cs.CL202053 cited

Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?

Yada Pruksachatkun, Jason Phang, Haokun Liu +6

While pretrained models such as BERT have shown large gains across natural language understanding tasks, their performance can be improved by further training the model on a data-r…