2 |
Discovering changes in birthing narratives during COVID-19 ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
A Survey on Recognizing Textual Entailment as an NLP Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Probing Neural Language Models for Human Tacit Assumptions ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
What do you learn from context? Probing for sentence structure in contextualized word representations ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
|
|
|
|
Abstract:
Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious correlations in data. We evaluate whether adversarial learning can be used in NLI to encourage models to learn representa- tions free of hypothesis-only biases. Our analyses indicate that the representations learned via adversarial learning may be less biased, with only small drops in NLI accuracy. ; Accepted Manuscript
|
|
URL: http://nrs.harvard.edu/urn-3:HUL.InstRepos:40827358
|
|
BASE
|
|
Hide details
|
|
8 |
Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Efficient, Compositional, Order-Sensitive N-Gram Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|