26 citations · 74 across the 49 of their papers we have counts for
11 papers · 1 filter
On the Curious Case of norm of Sense Embeddings
Yi Zhou, Danushka Bollegala
We show that the norm of a static sense embedding encodes information related to the frequency of that sense in the training corpus used to learn the sense embeddings. Thi…
Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki
We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs), and find that there exists…
Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation
Xiaohang Tang, Yi Zhou, Danushka Bollegala
Dynamic contextualised word embeddings (DCWEs) represent the temporal semantic variations of words. We propose a method for learning DCWEs by time-adapting a pretrained Masked Lang…
Random projections and Kernelised Leave One Cluster Out Cross-Validation: Universal baselines and evaluation tools for supervised machine learning for materials properties
Samantha Durdy, Michael Gaultois, Vladimir Gusev +2
With machine learning being a popular topic in current computational materials science literature, creating representations for compounds has become common place. These representat…
Gender Bias in Masked Language Models for Multiple Languages
Masahiro Kaneko, Aizhan Imankulova, Danushka Bollegala +1
Masked Language Models (MLMs) pre-trained by predicting masked tokens on large corpora have been used successfully in natural language processing tasks for a variety of languages.…
Gender Bias in Meta-Embeddings
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki
Different methods have been proposed to develop meta-embeddings from a given set of source embeddings. However, the source embeddings can contain unfair gender-related biases, and…
A Survey on Word Meta-Embedding Learning
Danushka Bollegala, James O'Neill
Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ab…
Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models
Keigo Takahashi, Danushka Bollegala
A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However…
Position-based Prompting for Health Outcome Generation
M. Abaho, D. Bollegala, P. Williamson +1
Probing Pre-trained Language Models (PLMs) using prompts has indirectly implied that language models (LMs) can be treated as knowledge bases. To this end, this phenomena has been e…
Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings
Yi Zhou, Masahiro Kaneko, Danushka Bollegala
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other s…
Assessment of contextualised representations in detecting outcome phrases in clinical trials
Micheal Abaho, Danushka Bollegala, Paula R Williamson +1
Automating the recognition of outcomes reported in clinical trials using machine learning has a huge potential of speeding up access to evidence necessary in healthcare decision-ma…