Quantifying social biases in NLP: A generalization and empirical comparison of extrinsic fairness metrics
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 …
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
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 …
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
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 …
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
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 …
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
Inflectional values, such as singular and plural, sustain agreement relations between
constituents in sentences, allowing sentence parsing and prediction in online processing …
constituents in sentences, allowing sentence parsing and prediction in online processing …
[HTML][HTML] An information-theoretic analysis of targeted regressions during reading
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 …
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
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 …
reach language equality in future Natural Language Processing technologies. Free-order …
What about the precedent: An information-theoretic analysis of common law
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 …
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 …
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
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 …
grammatical categories. How similar are these gender systems across languages? To …