Probing pretrained language models for lexical semantics
The success of large pretrained language models (LMs) such as BERT and RoBERTa has
sparked interest in probing their representations, in order to unveil what types of knowledge …
sparked interest in probing their representations, in order to unveil what types of knowledge …
Visually grounded reasoning across languages and cultures
The design of widespread vision-and-language datasets and pre-trained encoders directly
adopts, or draws inspiration from, the concepts and images of ImageNet. While one can …
adopts, or draws inspiration from, the concepts and images of ImageNet. While one can …
Sustainable modular debiasing of language models
A Lauscher, T Lueken, G Glavaš - arXiv preprint arXiv:2109.03646, 2021 - arxiv.org
Unfair stereotypical biases (eg, gender, racial, or religious biases) encoded in modern
pretrained language models (PLMs) have negative ethical implications for widespread …
pretrained language models (PLMs) have negative ethical implications for widespread …
XCOPA: A multilingual dataset for causal commonsense reasoning
In order to simulate human language capacity, natural language processing systems must
be able to reason about the dynamics of everyday situations, including their possible causes …
be able to reason about the dynamics of everyday situations, including their possible causes …
[PDF][PDF] Measuring fairness with biased rulers: A comparative study on bias metrics for pre-trained language models
An increasing awareness of biased patterns in natural language processing resources such
as BERT has motivated many metrics to quantify 'bias' and 'fairness' in these resources …
as BERT has motivated many metrics to quantify 'bias' and 'fairness' in these resources …
Fast, effective, and self-supervised: Transforming masked language models into universal lexical and sentence encoders
Pretrained Masked Language Models (MLMs) have revolutionised NLP in recent years.
However, previous work has indicated that off-the-shelf MLMs are not effective as universal …
However, previous work has indicated that off-the-shelf MLMs are not effective as universal …
On the independence of association bias and empirical fairness in language models
The societal impact of pre-trained language models has prompted researchers to probe
them for strong associations between protected attributes and value-loaded terms, from slur …
them for strong associations between protected attributes and value-loaded terms, from slur …
Revisiting non-English text simplification: A unified multilingual benchmark
Recent advancements in high-quality, large-scale English resources have pushed the
frontier of English Automatic Text Simplification (ATS) research. However, less work has …
frontier of English Automatic Text Simplification (ATS) research. However, less work has …
From word types to tokens and back: A survey of approaches to word meaning representation and interpretation
M Apidianaki - Computational Linguistics, 2023 - direct.mit.edu
Vector-based word representation paradigms situate lexical meaning at different levels of
abstraction. Distributional and static embedding models generate a single vector per word …
abstraction. Distributional and static embedding models generate a single vector per word …
Simreluz: Similarity and relatedness scores as a semantic evaluation dataset for uzbek language
Semantic relatedness between words is one of the core concepts in natural language
processing, thus making semantic evaluation an important task. In this paper, we present a …
processing, thus making semantic evaluation an important task. In this paper, we present a …