26 citations · 74 across the 49 of their papers we have counts for
13 papers · 1 filter
A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models
Yi Zhou, Jose Camacho-Collados, Danushka Bollegala
Various types of social biases have been reported with pretrained Masked Language Models (MLMs) in prior work. However, multiple underlying factors are associated with an MLM such…
Can Word Sense Distribution Detect Semantic Changes of Words?
Xiaohang Tang, Yi Zhou, Taichi Aida +2
Semantic Change Detection (SCD) of words is an important task for various NLP applications that must make time-sensitive predictions. Some words are used over time in novel ways to…
-- Predicting the Semantic Changes in Words across Corpora by Context Swapping
Taichi Aida, Danushka Bollegala
Meanings of words change over time and across domains. Detecting the semantic changes of words is an important task for various NLP applications that must make time-sensitive predi…
The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki
Pre-trained language models trained on large-scale data have learned serious levels of social biases. Consequently, various methods have been proposed to debias pre-trained models.…
In-Contextual Gender Bias Suppression for Large Language Models
Daisuke Oba, Masahiro Kaneko, Danushka Bollegala
Despite their impressive performance in a wide range of NLP tasks, Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. Prior work has propos…
Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders
Guanqun Cao, Jiaqi Jiang, Danushka Bollegala +1
The missing signal caused by the objects being occluded or an unstable sensor is a common challenge during data collection. Such missing signals will adversely affect the results o…
Multimodal Zero-Shot Learning for Tactile Texture Recognition
Guanqun Cao, Jiaqi Jiang, Danushka Bollegala +2
Tactile sensing plays an irreplaceable role in robotic material recognition. It enables robots to distinguish material properties such as their local geometry and textures, especia…
Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings
Haochen Luo, Yi Zhou, Danushka Bollegala
Sense embedding learning methods learn multiple vectors for a given ambiguous word, corresponding to its different word senses. For this purpose, different methods have been propos…
Metrics for quantifying isotropy in high dimensional unsupervised clustering tasks in a materials context
Samantha Durdy, Michael W. Gaultois, Vladimir Gusev +2
Clustering is a common task in machine learning, but clusters of unlabelled data can be hard to quantify. The application of clustering algorithms in chemistry is often dependant o…
Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting
Saeth Wannasuphoprasit, Yi Zhou, Danushka Bollegala
Cosine similarity between two words, computed using their contextualised token embeddings obtained from masked language models (MLMs) such as BERT has shown to underestimate the ac…
Evaluating the Robustness of Discrete Prompts
Yoichi Ishibashi, Danushka Bollegala, Katsuhito Sudoh +1
Discrete prompts have been used for fine-tuning Pre-trained Language Models for diverse NLP tasks. In particular, automatic methods that generate discrete prompts from a small set…
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki
Numerous types of social biases have been identified in pre-trained language models (PLMs), and various intrinsic bias evaluation measures have been proposed for quantifying those…
Vis2Hap: Vision-based Haptic Rendering by Cross-modal Generation
Guanqun Cao, Jiaqi Jiang, Ningtao Mao +3
To assist robots in teleoperation tasks, haptic rendering which allows human operators access a virtual touch feeling has been developed in recent years. Most previous haptic rende…