4 citations · 10 across the 14 of their papers we have counts for
15 papers
WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution
Yi Zhou, Kiamehr Rezaee, Danushka Bollegala +2
Word-in-Context (WiC) remains challenging for language models, despite recent progress on lexical-semantic tasks. We hypothesise that this difficulty arises not only from comparing…
Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models
Gaifan Zhang, Yi Zhou, Danushka Bollegala
Semantic similarity between two sentences depends on the aspects considered between those sentences. To study this phenomenon, Deshpande et al. (2023) proposed the Conditional Sema…
CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
Gaifan Zhang, Yi Zhou, Danushka Bollegala
The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence embedding methods, it remains unclear as how to best modify a…
Evaluating the Effect of Retrieval Augmentation on Social Biases
Tianhui Zhang, Yi Zhou, Danushka Bollegala
Retrieval Augmented Generation (RAG) has gained popularity as a method for conveniently incorporating novel facts that were not seen during the pre-training stage in Large Language…
Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models
Yi Zhou, Danushka Bollegala, Jose Camacho-Collados
Social biases such as gender or racial biases have been reported in language models (LMs), including Masked Language Models (MLMs). Given that MLMs are continuously trained with in…
Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings
Gaifan Zhang, Yi Zhou, Danushka Bollegala
Sentence embeddings produced by Pretrained Language Models (PLMs) have received wide attention from the NLP community due to their superior performance when representing texts in n…
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…
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…
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…
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…
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…
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…
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy
Yi Zhou, Danushka Bollegala
Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well it…
Spatio-temporal Attention Model for Tactile Texture Recognition
Guanqun Cao, Yi Zhou, Danushka Bollegala +1
Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation. A detailed unde…