350 citations · 652 across the 49 of their papers we have counts for
58 papers
Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
Yassir Fathullah, Mark J. F. Gales
This paper explores generalised probabilistic modelling and uncertainty estimation in comparative LLM-as-a-judge frameworks. We show that existing Product-of-Experts methods are sp…
Grammatical Error Feedback: An Implicit Evaluation Approach
Stefano Bannò, Kate Knill, Mark J. F. Gales
Grammatical feedback is crucial for consolidating second language (L2) learning. Most research in computer-assisted language learning has focused on feedback through grammatical er…
Learn and Don't Forget: Adding a New Language to ASR Foundation Models
Mengjie Qian, Siyuan Tang, Rao Ma +2
Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, langua…
Efficient Sample-Specific Encoder Perturbations
Yassir Fathullah, Mark J. F. Gales
Encoder-decoder foundation models have displayed state-of-the-art performance on a range of autoregressive sequence tasks. This paper proposes a simple and lightweight modification…
Can GPT-4 do L2 analytic assessment?
Stefano Bannò, Hari Krishna Vydana, Kate M. Knill +1
Automated essay scoring (AES) to evaluate second language (L2) proficiency has been a firmly established technology used in educational contexts for decades. Although holistic scor…
Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Rao Ma, Adian Liusie, Mark J. F. Gales +1
Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings.…
Towards End-to-End Spoken Grammatical Error Correction
Stefano Bannò, Rao Ma, Mengjie Qian +2
Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar whe…
Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Adian Liusie, Potsawee Manakul, Mark J. F. Gales
Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performan…
Zero-shot Audio Topic Reranking using Large Language Models
Mengjie Qian, Rao Ma, Adian Liusie +3
Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far…
Analyzing Multiple-Choice Reading and Listening Comprehension Tests
Vatsal Raina, Adian Liusie, Mark Gales
Multiple-choice reading and listening comprehension tests are an important part of language assessment. Content creators for standard educational tests need to carefully curate que…
Adapting an ASR Foundation Model for Spoken Language Assessment
Rao Ma, Mengjie Qian, Mark J. F. Gales +1
A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper ha…
LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models
Adian Liusie, Potsawee Manakul, Mark J. F. Gales
Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these syste…
Can Generative Large Language Models Perform ASR Error Correction?
Rao Ma, Mengjie Qian, Potsawee Manakul +2
ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using…
Sentiment Perception Adversarial Attacks on Neural Machine Translation Systems
Vyas Raina, Mark Gales
With the advent of deep learning methods, Neural Machine Translation (NMT) systems have become increasingly powerful. However, deep learning based systems are susceptible to advers…
Sample Attackability in Natural Language Adversarial Attacks
Vyas Raina, Mark Gales
Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts hav…
CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models
Potsawee Manakul, Yassir Fathullah, Adian Liusie +3
In this paper, we consider the challenge of summarizing patients' medical progress notes in a limited data setting. For the Problem List Summarization (shared task 1A) at the BioNL…
Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution
Adian Liusie, Vatsal Raina, Andrew Mullooly +2
Multiple choice exams are widely used to assess candidates across a diverse range of domains and tasks. To moderate question quality, newly proposed questions often pass through pr…
Adapting an Unadaptable ASR System
Rao Ma, Mengjie Qian, Mark J. F. Gales +1
As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than…
Multi-Head State Space Model for Speech Recognition
Yassir Fathullah, Chunyang Wu, Yuan Shangguan +8
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. I…
Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties
Yassir Fathullah, Guoxuan Xia, Mark Gales
Efficiently and reliably estimating uncertainty is an important objective in deep learning. It is especially pertinent to autoregressive sequence tasks, where training and inferenc…
Ensemble prosody prediction for expressive speech synthesis
Tian Huey Teh, Vivian Hu, Devang S Ram Mohan +7
Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended t…
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Potsawee Manakul, Adian Liusie, Mark J. F. Gales
Generative Large Language Models (LLMs) such as GPT-3 are capable of generating highly fluent responses to a wide variety of user prompts. However, LLMs are known to hallucinate fa…
N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space
Rao Ma, Mark J. F. Gales, Kate M. Knill +1
Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions. Most prior works use…
Identifying Adversarially Attackable and Robust Samples
Vyas Raina, Mark Gales
Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research…