Skip to search formSkip to main contentSkip to account menu
Challenges in Automated Debiasing for Toxic Language Detection
TLDR
The findings show that debiasing a model trained on biased toxic language data is not as effective as simply relabeling the data to remove existing biases, and proposes an automatic, dialect-aware data correction method, as a proof-of-concept.
View on ACL
Evaluating Commonsense in Pre-trained Language Models
TLDR
This work studies the commonsense ability of GPT, BERT, XLNet, and RoBERTa by testing them on seven challenging benchmarks, finding that language modeling and its variants are effective objectives for promoting models' commonsens ability while bi-directional context and larger training set are bonuses.
View PDF on arXiv
Multilevel Text Alignment with Cross-Document Attention
TLDR
This work proposes a new learning approach that equips previously established hierarchical attention encoders for representing documents with a cross-document attention component, enabling structural comparisons across different levels (document-to-document and sentence- to-document).
View on ACL
Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection
TLDR
This work disentangle what is annotated as toxic by considering posts with three characteristics: anti-Black language, African American English dialect, and vulgarity, and shows strong associations between annotator identity and beliefs and their ratings of toxicity.
View on ACL
Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets
TLDR
This work proposes a Linguistically-Informed Transformation (LIT) method to automatically generate contrast sets, which enables practitioners to explore linguistic phenomena of interests as well as compose different phenomena.
View on ACL
Learning to translate by learning to communicate
TLDR
Two variants of EC Fine-Tuning are presented, one of which outperforms a backtranslation-based baseline in 6/8 translation settings, and proves especially beneficial for the very low-resource languages of Nepali and Sinhala.
View PDF on arXiv
RPD: A Distance Function Between Word Embeddings
TLDR
This paper proposes a novel metric called Relative Pairwise Inner Product Distance (RPD) to quantify the distance between different sets of word embeddings and investigates the influence of different training processes and corpora to shed light on the poorly understood word embedDings.
View on ACL
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License