Search Results for author:
Found 32 papers, 10 papers with code
Speak & Improve Challenge 2025: Tasks and Baseline Systems
Linked with the challenge, the Speak & Improve (S&I) Corpus 2025 is being pre-released, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Speak & Improve Corpus 2025: an L2 English Speech Corpus for Language Assessment and Feedback
This enables a range of language-learning tasks to be examined, such as assessing speaking proficiency or providing feedback on grammatical errors in a learner's speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Grammatical Error Feedback: An Implicit Evaluation Approach
Most research in computer-assisted language learning has focused on feedback through grammatical error correction (GEC) systems, rather than examining more holistic feedback that may be more useful for learners.
Learn and Don't Forget: Adding a New Language to ASR Foundation Models
If only adaptation parameters are used, the language capabilities are maintained but at the cost of performance in the new language.
Can GPT-4 do L2 analytic assessment?
Automated essay scoring (AES) to evaluate second language (L2) proficiency has been a firmly established technology used in educational contexts for decades.
WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models
Watermarking generative-AI systems, such as LLMs, has gained considerable interest, driven by their enhanced capabilities across a wide range of tasks.
Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks.
Investigating the Emergent Audio Classification Ability of ASR Foundation Models
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
This foundation model can be used to replace the whole framework or part of it, e. g., ASR and disfluency removal.
Zero-shot Audio Topic Reranking using Large Language Models
To gain a deeper understanding and further insights into the performance differences and limitations of these text sources, we employ a fact-checking approach to analyse the information consistency among them.
Mitigating Word Bias in Zero-shot Prompt-based Classifiers
To address this problem, it is possible to optimise classification thresholds on a labelled data set, however, this mitigates some of the advantages of prompt-based classifiers.
LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models
Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks.
Adapting an ASR Foundation Model for Spoken Language Assessment
Additionally, these models have a tendency to skip disfluencies and hesitations in the output.
Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution
Multiple choice exams are widely used to assess candidates across a diverse range of domains and tasks.
Adapting an Unadaptable ASR System
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 having direct access to models themselves.
Multi-Head State Space Model for Speech Recognition
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches.
Ranked #10 on
Speech Recognition
on LibriSpeech test-clean
Who Needs Decoders? Efficient Estimation of Sequence-level Attributes
In these scenarios, where for example knowing the quality of a system's output to predict poor performance prevails over knowing the output itself, is it possible to bypass the autoregressive decoding?
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
In this work, we propose "SelfCheckGPT", a simple sampling-based approach that can be used to fact-check the responses of black-box models in a zero-resource fashion, i. e. without an external database.
N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space
Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization
In this work, we introduce an alternative scheme based on standard information-theoretic measures in which the information present in the source and summary is directly compared.
L2 proficiency assessment using self-supervised speech representations
Though the wav2vec 2. 0 based system is found to be sensitive to the nature of the response, it can be configured to yield comparable performance to systems requiring a speech transcription, and yields gains when appropriately combined with standard approaches.
Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods
The podcast summary assessment data is available.
Shifts 2.0: Extending The Dataset of Real Distributional Shifts
This creates a need to be able to assess how robustly ML models generalize as well as the quality of their uncertainty estimates.
Self-Distribution Distillation: Efficient Uncertainty Estimation
Furthermore it is possible to build ensembles of these models and apply hierarchical ensemble distillation approaches.
Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems
Second, we propose a modified architecture that selects the subset of sentences to constrain the encoder-decoder attention.
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
However, many tasks of practical interest have different modalities, such as tabular data, audio, text, or sensor data, which offer significant challenges involving regression and discrete or continuous structured prediction.
Ranked #2 on
Weather Forecasting
on Shifts
An Initial Investigation of Non-Native Spoken Question-Answering
The SQA task considered in this paper is to extract the answer from a candidate$\text{'}$s spoken response to a question in a prompt-response style language assessment test.
Long-Span Summarization via Local Attention and Content Selection
Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization.
Attention Forcing for Machine Translation
This approach guides the model with the generated output history and reference attention, and can reduce the training-inference mismatch without a schedule or a classifier.
Non-native Speaker Verification for Spoken Language Assessment
These systems are explored for non-native spoken English data in this paper.
Attention Forcing for Sequence-to-sequence Model Training
This paper introduces attention forcing, which guides the model with generated output history and reference attention.
