Quantifying social biases in NLP: A generalization and empirical comparison of extrinsic fairness metrics

P Czarnowska, Y Vyas, K Shah - Transactions of the Association for …, 2021 - direct.mit.edu
Measuring bias is key for better understanding and addressing unfairness in NLP/ML
models. This is often done via fairness metrics, which quantify the differences in a model's …

Are larger pretrained language models uniformly better? comparing performance at the instance level

R Zhong, D Ghosh, D Klein, J Steinhardt - arXiv preprint arXiv:2105.06020, 2021 - arxiv.org
Larger language models have higher accuracy on average, but are they better on every
single instance (datapoint)? Some work suggests larger models have higher out-of …

Generalising to German plural noun classes, from the perspective of a recurrent neural network

V Dankers, A Langedijk, K McCurdy… - Proceedings of the …, 2021 - aclanthology.org
Inflectional morphology has since long been a useful testing ground for broader questions
about generalisation in language and the viability of neural network models as cognitive …

A song of (dis) agreement: Evaluating the evaluation of explainable artificial intelligence in natural language processing

M Neely, SF Schouten, M Bleeker… - HHAI2022: Augmenting …, 2022 - ebooks.iospress.nl
There has been significant debate in the NLP community about whether or not attention
weights can be used as an explanation–a mechanism for interpreting how important each …

Form and function: A study on the distribution of the inflectional endings in Italian nouns and adjectives

VN Pescuma, C Zanini, D Crepaldi… - Frontiers in …, 2021 - frontiersin.org
Inflectional values, such as singular and plural, sustain agreement relations between
constituents in sentences, allowing sentence parsing and prediction in online processing …

[HTML][HTML] An information-theoretic analysis of targeted regressions during reading

EG Wilcox, T Pimentel, C Meister, R Cotterell - Cognition, 2024 - Elsevier
Regressions, or backward saccades, are common during reading, accounting for between
5% and 20% of all saccades. And yet, relatively little is known about what causes them. We …

On the difficulty of translating free-order case-marking languages

A Bisazza, A Üstün, S Sportel - Transactions of the Association for …, 2021 - direct.mit.edu
Identifying factors that make certain languages harder to model than others is essential to
reach language equality in future Natural Language Processing technologies. Free-order …

What about the precedent: An information-theoretic analysis of common law

J Valvoda, T Pimentel, N Stoehr, R Cotterell… - arXiv preprint arXiv …, 2021 - arxiv.org
In common law, the outcome of a new case is determined mostly by precedent cases, rather
than by existing statutes. However, how exactly does the precedent influence the outcome of …

Are Female Carpenters like Blue Bananas? A Corpus Investigation of Occupation Gender Typicality

D Ju, K Ulrich, A Williams - arXiv preprint arXiv:2408.02948, 2024 - arxiv.org
People tend to use language to mention surprising properties of events: for example, when a
banana is blue, we are more likely to mention color than when it is yellow. This fact is taken …

Measuring the similarity of grammatical gender systems by comparing partitions

AD McCarthy, A Williams, S Liu… - Proceedings of the …, 2020 - aclanthology.org
A grammatical gender system divides a lexicon into a small number of relatively fixed
grammatical categories. How similar are these gender systems across languages? To …