CardiffNLP

Seminar: "Prying the LLM Blackbox Open: Towards Interpretable, Controllable, and Composable AI"

Thu, 05 Mar 2026 13:00:00 +0000

Invited Speaker: Jingcheng (Frank) Niu (UKP, TU Darmstadt)

Short Bio: Jingcheng (Frank) Niu is a Postdoctoral Researcher at the UKP Lab at TU Darmstadt, where he works on mechanistic interpretability to uncover the internal structures and computational mechanisms that enable large language models (LLMs) to perform a wide range of tasks. He received his PhD in Computer Science from the University of Toronto. His research has been recognized with multiple awards, including an ACL 2025 Outstanding Paper Award, a TMLR J2C Certification.

Seminar: "Efficient LLMs on the Edge"

Thu, 05 Feb 2026 13:00:00 +0000

Invited Speaker: Cheng Deng (University of Edinburgh)

Short Bio: Cheng is a Research Fellow at the Bayes Centre, University of Edinburgh, where he works in collaboration with Prof. Luo Mai, Prof. Jeff Pan, and Prof. Jun Wang. His research interest is efficient LLM. He also serves as a Guest Researcher at Li Auto. Prior to joining the University of Edinburgh, he was a Research Scientist at Huawei London Research Centre. Before that, Cheng worked as a Research Assistant at the Hong Kong University of Science and Technology (Guangzhou), collaborating with Prof. Lei Chen and Prof. Lionel M. Ni. He obtained his Ph.D. in Computer Science from the Acemap IIoT Lab at Shanghai Jiao Tong University under the supervision of Prof. Xinbing Wang. During his early research career, he interned with the Data Team at TikTok and served as an Applied Scientist at the Amazon Shanghai AI Lab. In 2021, he was selected for the Wenjun Wu Honored Ph.D. Class. Cheng has published over 30 papers in top-tier conferences and journals, including ICML, NeurIPS, ICLR, MLSys, and IEEE TMC, and currently serves as a reviewer for venues such as ICLR, ACL, NeurIPS, ICML, and CVPR.

Seminar: "Reframing Content Moderation: Guideline-Driven and Explainable Hate Speech Detection"

Thu, 15 Jan 2026 13:00:00 +0000

Invited Speaker: Agostina Calabrese(University of Edinburgh)

Short Bio: Agostina Calabrese is a final-year Ph.D. student at the UKRI Centre for Doctoral Training in NLP at The University of Edinburgh, where she works on policy-aware explainable abuse detection under the supervision of Björn Ross and Mirella Lapata. Her research focuses on developing models that align with platform-specific moderation policies while remaining transparent and explainable, demonstrating how this approach can significantly reduce costs in real-world moderation pipelines. She is a member of the EdinburghNLP group based at the Institute for Language, Cognition and Computation (ILCC). She has worked as a Research Intern in the Computational Social Science team at Snap Inc. (Fall 2023) and in the Assistant AI team at Meta Reality Labs (Fall 2022). Previously, she was a Research Fellow at Sapienza NLP (Sapienza University of Rome), where she worked on multimodal systems for language–vision tasks and on the development of BabelPic. She holds a Bachelor’s degree (2017) and a Master’s degree (2019) in Computer Science from Sapienza University of Rome, both awarded with full marks and honors (110/110 cum laude). She is also actively involved in the NLP community around online safety. She co-organised the 8th and 9th Workshop on Online Abuse and Harms (2024, 2025), and in 2022, she created a Slack community for researchers and practitioners working on hate speech and related topics. As of June 2025, the community includes over 250 members from academia and industry.

Seminar: "Evaluating Pluralism in LLMs and Understanding Ambiguity in NLP Tasks"

Thu, 11 Dec 2025 13:00:00 +0000

Invited Speaker 1: Laura Majer (University of Zagreb)

Title: “Evaluating Pluralism in LLMs through Latent Perspectives”

Abstract: In NLP, linguistic diversity and disagreement are mainly acknowledged through two paradigms: perspectivism and pluralism. Perspectivism argues for preserving unaggregated labels throughout the NLP pipeline, where ‘perspective’ is usually represented as a set of static labels, and open-ended text analysis is rare. In parallel, pluralism refers to the analysis of LLM diversity, with prior work showing that LLMs exhibit notable homogeneity in generated text. This talk will showcase current work that extends the evaluation of pluralism in LLMs by estimating latent perspectives from open-ended text. By analysing the overlap between human and LLM-generated book reviews at multiple levels of abstraction, the goal is to identify the specific ways LLMs constrain diversity in their output and to propose potential remedies.

Bio: Laura is a third-year PhD student at the University of Zagreb, focusing on Natural Language Processing. She previously worked on various subjective tasks, a European fact-checking initiative, and synthetic data evaluation. Currently, she is primarily interested in perspectivism, pluralism, and annotation setups in subjective scenarios. In parallel, she is employed as a Research Engineer in industry.

Invited Speaker 2: Ieva Staliūnaitė (University of Cambridge)

Title: “Distinguishing Wanted and Unwanted Uncertainty: Ambiguity in NLP Tasks”

Abstract: Annotators sometimes disagree, and models are sometimes uncertain. This happens for different reasons, and is manifested differently across NLP tasks. This talk will discuss the different interactions between model probability distributions and human label variation. In automated fact-checking, underspecification is a powerful tool for the potential of misinformation. In Machine Translation, bias can lead to very confident predictions even in cases where gender is ambiguous. In LLM generations, uncertainty is canonically taken to be taken as a signal for incorrectness, however this varies depending on the calibration of the model and the ambiguity of the task. Across tasks, disagreement can be both valid and noisy, and separating the two is important.

Bio: Ieva is a fourth year PhD student at the University of Cambridge, working on Natural Language Processing. Her work focuses on fact-checking, ambiguity and uncertainty. She has a background in Linguistics from Utrecht University. She is currently working on a project on LLM correctness prediction and uncertainty quantification at the Alan Turing Institute. Ieva is open to job opportunities in academia and industry post-PhD!

Seminar: "Towards AI Readiness in Auditing: Benchmarks, Models, and Domain-Structured Reasoning"

Thu, 04 Dec 2025 13:00:00 +0000

Invited Speaker: Jimin Huang

Short Bio: Jimin Huang is the founder of The Fin AI community, an initiative dedicated to advancing open science, tooling, and model development for the financial services industry with a focus on responsible innovation. The Fin AI is now an associated member of FINOS and a collaborator with the NVIDIA AI Technology Center (NVAITC). Jimin is also an associated member of The National Centre for Text Mining (NaCTeM). His research spans natural language processing and computational finance, with a particular emphasis on financial large language models (LLMs) and open-source contributions. He is the organizer of the FinLLM Challenge at FinNLP-AgentScen @ IJCAI-2024 and serves as the general chair for The Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal).

Seminar: "EMNLP 2025 (and Other Recent Venues) Paper Highlights"

Thu, 20 Nov 2025 13:00:00 +0000

Seminar: "Measuring Distributional Realism in Synthetic Query-Passage Datasets for Information Retrieval"

Thu, 13 Nov 2025 13:00:00 +0000

Invited Speaker: Marco Cuccarini

Seminar: "Short NLP Presentations"

Thu, 23 Oct 2025 13:00:00 +0000

Invited Speakers: Marta Vazquez Abuin, Jingxuan Chen, Nico Potyka and Christian Arnold

Seminar: "What Shapes the Future of Natural Language Processing Research? A Meta Perspective"

Thu, 09 Oct 2025 13:00:00 +0000

Invited Speaker: Jan Philip Wahle (University of Göttingen)

Bio: Jan Philip Wahle is a research fellow in computer science at the University of Göttingen in Germany. He received his Master’s degree in computer science from the University of Wuppertal and worked for the automotive company Aptiv PLC before continuing with his Ph.D. studies. During his Ph.D., Jan has been a visiting researcher at the National Research Council of Canada. His research has been presented at ACL, EMNLP, EACL (among others). One of his research interests lies in gaining a deeper understanding of the dynamics of the NLP research field from a meta-perspective, particularly in identifying certain tendencies and biases within it. These days, he also manages third-party projects to advance low-resource models for historical German texts and projects related to AI safety and interpretability.

Seminar: "Metaphor Processing and Low-Resource LLMs"

Thu, 25 Sep 2025 13:00:00 +0000

Invited Speaker 1: Elisa Sanchez Bayona

Title: “From Automatic Metaphor Processing in Spanish to a Multilingual Perspective: Annotation, Systems, and Evaluation”

Abstract: Metaphors are pervasive in our daily utterances, which is why the automatic processing of metaphorical expressions has gained popularity in the NLP field. Specifically, we explore the tasks of metaphor detection and interpretation and how language models respond to this cognitive-linguistic phenomenon from a cross-lingual perspective.

Invited Speaker 2: Joseba Fernandez de Landa Aguirre

Title: “Instructing Large Language Models for Low-Resource Languages”

Abstract: Instruction-tuned, open-weight LLMs for low-resourced languages are still rare, due challenges such as the lack of instruction datasets. For Basque, we leveraged the largest available corpora, evaluation benchmarks, and a new training strategy to develop a model that performs on par with proprietary systems. Beyond benchmark success over open weighted backbone models, our model was validated in a community LLM evaluation arena. Future work will explore applications in domain-specific contexts such as legal texts, news, and parliamentary discourse.

Seminar: "Modelling the Language of Extremist Groups"

Thu, 07 Aug 2025 13:00:00 +0000

Invited Speaker: Christine de Kock (University of Melbourne)

Bio: Dr Christine de Kock is an assistant professor in the School for Computing and Information Systems at the University of Melbourne. Her research explores topics in computational sociolinguistics, with a particular focus on harmful online behaviour. She completed her PhD in the Natural Language and Information Processing group at Cambridge.

Seminar: "NOLIMA: Long-Context Evaluation Beyond Literal Matching"

Thu, 19 Jun 2025 13:00:00 +0000

Invited Speaker: Ali Modaressi (LMU Munich)

Bio: I am a third-year PhD student at the Center for Information and Language Processing (CIS) at LMU Munich, working under the supervision of Prof. Hinrich Schütze. My current research focuses on memory-augmented large language models, and, more broadly, on long-context language modeling. Closely related, I have also worked on interactive language generation and information extraction. My NLP journey began during my MSc, supervised by Mohammad Taher Pilehvar, where I worked on explainability methods and interpretability of pre-trained language models–an area that remains relevant to my current research, particularly in analyzing retrieval models and knowledge probing.

Seminar: "Incorporating Sociolinguistic Theories for a Better Modeling of the Arabic Varieties"

Thu, 08 May 2025 13:00:00 +0000

Invited Speaker: Amr Keleg (University of Edinburgh)

Bio: Amr is a final-year PhD student at the University of Edinburgh. His research has so far focused on improving how the variation among Arabic dialects is modeled in NLP. He made multiple contributions to this end and received an outstanding paper award at ACL 2024. His work on Arabic dialects has increased his awareness of the cultural differences across Arabic-speaking communities. In the future, he is keen on extending his research to multilingual and multicultural settings.

Seminar: "OmniBench, Towards The Future of Universal Omni-Language Models"

Thu, 01 May 2025 13:00:00 +0000

Invited Speaker: Yizhi Li (University of Manchester)

Seminar: "SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation"

Thu, 27 Mar 2025 13:00:00 +0000

Invited Speaker: Jingxuan Chen (Huawei)

4th Cardiff NLP Summer Workshop

Wed, 19 Mar 2025 00:00:00 +0000

We are happy to announce the 4th Cardiff NLP Summer Workshop on July 14-15 2025!

This workshop will be an opportunity for participants to interact and attend talks/tutorials from high-profile NLP researchers from industry and academia.

Registration is free. Submit your Expression of Interest by April 11. More information here.

Seminar: "Making Complex Language Easier to Understand"

Thu, 13 Mar 2025 13:00:00 +0000

Invited Speaker: Matthew Shardlow (Manchester Metropolitan University)

Bio: Dr. Matthew Shardlow is a reader in Natural Language Processing in the Department of Computing and Mathematics at the Manchester Metropolitan University. He previously was part of the Horizon 2020 funded OpenMinTeD project and studied his PhD at the University of Manchester under an EPSRC funded Centre for doctoral training. He currently leads projects with industry partners including international publicly traded companies and local government. He is an organiser of the Text Simplification, Accessibility and Readability workshop (EMNLP 2022, RANLP 2023, EMNLP 2024, EMNLP 2025), the SemEval-2021 shared task on Lexical Complexity Prediction (ACL 2021), The TSAR-2022 shared task on lexical simplification (EMNLP2022) and the BEA-2024 MLSP shared task (NAACL 2024). His research interests lie in the field of distributional semantics and particularly the application of machine learning techniques to natural language tasks. He has previously worked on topics including named entity recognition, event extraction, machine translation, emoji semantics, text generation and has more recently explored phenomena of consciousness and anthropomorphisation in association to LLMs.

Seminar: "NLP and CSS: Lessons from One for the Other"

Thu, 20 Feb 2025 13:00:00 +0000

Invited Speaker: Arnav Arora (University of Copenhagen)

Bio: Arnav Arora is a PhD Student studying Natural Language Processing (NLP) at the University of Copenhagen. His primary research interests lie at the intersection of NLP and Computational Social Science, focusing on online harms such as misinformation and hate speech in low resource scenarios. Through his work, he aims to contribute to the development of equitable technology. Prior to this, he spent some time in industry as a Research Engineer at Checkstep, a content moderation company.

Seminar: "Preference Alignment, with Reference Mismatch, and without Reference Models"

Thu, 13 Feb 2025 13:00:00 +0000

Invited Speaker: James Thorne (KAIST Graduate School of AI)

Bio: James is Assistant Professor at the KAIST Graduate School of AI, South Korea, working on large-scale and knowledge-intensive natural language understanding. James recently completed his PhD at the University of Cambridge where he developed models and methods for automated fact verification and correction.

[1] https://aclanthology.org/2024.emnlp-main.626/

[2] https://arxiv.org/pdf/2406.06424

Seminar: "The Language of Standards: Aligning LLMs for Regulatory and Operational Compliance"

Thu, 30 Jan 2025 13:00:00 +0000

Invited Speaker: Joseph Marvin Imperial (University of Bath)

Seminar: "Prudent NLG Evaluation with Humans"

Thu, 16 Jan 2025 13:00:00 +0000

Invited Speaker: Vilém Zouhar (ETH Zürich, Switzerland)

Bio: Vilém is a PhD student at ETH Zürich working on both human and automatic evaluation of MT/NLG systems, balancing costs, quality, and bias.

Seminar: "NLP for Under-resourced African Languages"

Thu, 09 Jan 2025 13:00:00 +0000

Invited Speaker: Shamsuddeen Muhammad (Imperial College London)

New Research Associate Position

Mon, 25 Nov 2024 00:00:00 +0000

We are looking for a Research Associate to join the Cardiff NLP team in the School of Computer Science and Informatics at Cardiff University as part of Jose Camacho Chollados’s UKRI Future Leaders Fellowship, with flexibility and the chance to develop an independent research portfolio.

For an informal discussion about the role, please contact Prof. Jose Camacho Collados.

Application Deadline: 03 January 2025

Start Date: April 2025 (or soon afterwards)

Length: 15 months

Seminar: "The 'BERT moment' for Music - MERT: Large-Scale Self-supervised Training for Acoustic Music Understanding "

Thu, 21 Nov 2024 13:00:00 +0000

Invited Speaker: Chenghua Lin (University of Manchester)

Bio: Chenghua Lin is Professor of Natural Language Processing in the Department of Computer Science at The University of Manchester. His research focuses on integrating NLP and machine learning for language generation and understanding, with current key interests including AI for science, robustness in LLMs, evaluation methods and benchmarks, metaphor processing, and representation learning for music. He currently serves as the Secretary of the ACL SIGGEN Board, a member of the IEEE Speech and Language Processing Technical Committee, and is a founding advisor for the Multimodal Art Projection community. He has received several awards for his research, including the CIKM Test-of-Time Award and the INLG Best Paper Runner-up Award. He has also held numerous program and chairing roles for *ACL conferences, and is the lead organiser of the 1st and 2nd editions of the Lay Summarisation shared task, co-located with the BioNLP Workshop.

New Fully Funded PhD Scholarship

Tue, 19 Nov 2024 00:00:00 +0000

Full PhD scholarship available on a project related to natural language processing (NLP) to be supervised by Prof. Jose Camacho-Collados. The project will be linked with Jose’s current UKRI Future Leader Fellowship on natural language understanding and applications. The scope of the project is flexible, as long as it deals with NLP (including language understanding), language models or NLP applications, in particular in connection with computational social science but not limited to this area.

For more information about the project, please contact Prof. Jose Camacho Collados.

Application Deadline: 03 January 2025

Start Date: Flexible (April/July/October 2025)

Topic: Flexible, as long as related to NLP

Reading Group: "Puns, LLMs and Explainability"

Thu, 07 Nov 2024 13:00:00 +0000

Alessandro will focus on the paper “A good pun is its own reword”: Can Large Language Models Understand Puns? (Xu et al. EMNLP 2024), will prepare a short presentation and then we will have time for discussion

Another relevant paper that will be mentioned in the reading group including a pun dataset is: ExPUNations: Augmenting Puns with Keywords and Explanations (Sun et al. EMNLP 2022).

There is no need to read the papers in advance, but could be helpful to at least skim through them.

Seminar: "Natural Experiments in NLP and Where to Find Them"

Thu, 10 Oct 2024 13:00:00 +0000

Invited Speaker: Pietro Lesci (University of Cambridge)

Bio: Pietro Lesci is a PhD student in Natural Language Processing at the University of Cambridge, working with Professor Andreas Vlachos. His research explores the causal effects of training choices on language models, focusing on memorisation, shortcut learning, and tokenisation. His work has been presented at major NLP conferences like ACL and NAACL. He received a Best Paper Award at ACL 2024 and funding from the Translated Imminent Research Grant for his research contributions. Pietro’s experience spans academia and industry, including roles at Amazon AWS AI Labs, Bain & Company, and Bocconi University. He holds an MSc in Economic and Social Sciences from Bocconi University.

Seminar: "Atom-based Approaches to Creating Interpretable NLI Models"

Thu, 03 Oct 2024 13:00:00 +0000

Invited Speaker: Joe Stacey (Apple/Imperial College London)

Bio: Joe is an Apple AI/ML scholar in the 4th year of his PhD at Imperial College London, supervised by Marek Rei. Joe’s research involves creating more robust and interpretable NLP models, focusing on the task of Natural Language Inference. Prior to his PhD, Joe worked at PwC for 6 years as an analytics consultant, and also previously taught maths in a challenging secondary school.

Seminar: "Interpreting Transformer Decisions"

Thu, 06 Jun 2024 13:00:00 +0000

Invited Speaker: Mohammad Taher Pilehvar (Cardiff University)

Seminar: "Evaluating the Spatial Reasoning Capabilities of Large Language Models"

Thu, 23 May 2024 13:00:00 +0000

Invited Speaker: Anthony Cohn (University of Leeds)

Seminar: "Knowledge Representation and Large Language Models"

Thu, 16 May 2024 13:00:00 +0000

Invited Speaker 1: Zhiwei Hu

Title: Knowledge Representation Learning and Knowledge Distillation

Abstract: Knowledge Representation Learning (KRL) focus on learning meaningful representations of knowledge from raw data. In knowledge representation learning, the goal is to create models that can capture and represent the underlying structure and semantics of data in a way that is useful for various AI tasks such as reasoning, recommendation, and prediction. One of the main challenges in KRL is capturing the complexity and diversity of real-world knowledge, especially effectively integrating different types of information. In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral. How to elegantly make Small Language Models (SLMs) have the ability to compete with large models is a promising research direction.

Invited Speaker 2: Xiaoqi Han

Title: Model Editing in Pre-trained Language Models

Abstract: Even with their impressive capabilities, Large Language Models (LLMs) such as ChatGPT are not immune to issues of factual inaccuracies or logical inconsistencies. A key concern is how to seamlessly update these LLMs to correct mistakes without resorting to exhaustive retraining or continuous training procedures, both of which can require significant computational resources and time. Thus, the ability to edit LLMs offers an efficient solution to modify a model’s behavior, notably within a specific area of interest, without negatively impacting its performance on other tasks. Through this presentation, we seek to present a systematic and current overview of cutting-edge methods and provide insights into real-world applications and engage in discussions about future research directions.

Seminar: "Misinformed by Visualisations: Countering with Explainable Fact-Checking over Real-World Chart Images"

Thu, 07 Mar 2024 13:00:00 +0000

Invited Speaker: Mubashara Akhtar (King’s College London, UK)

Bio: Mubashara Akhtar is a final-year PhD student at King’s College London and a student researcher at Google DeepMind. Previously, she interned at Google DeepMind in Zurich and was a visiting student at the Cambridge NLP Group. She is also part of the organisation committee of the FEVER workshop and co-leading the responsible AI committee of Croissant, a MLCommons project on ML dataset documentation. Her research is on knowledge-grounded NLP, focusing on reasoning over text, tables, and images as modalities for automated fact-checking and question-answering. Her research interests further include understanding large language models’ reasoning capabilities, focusing on numeracy and factuality.

Seminar: "Context Mixing in Transformers"

Thu, 29 Feb 2024 13:00:00 +0000

Invited Speaker: Hosein Mohebbi (Tilburg University, Netherlands)

Bio: Hosein Mohebbi is a PhD candidate at the Department of Cognitive Science and Artificial Intelligence at Tilburg University, Netherlands. He is part of the InDeep consortium project, doing research on interpretability of deep neural models for text and speech. His research has been published in leading NLP venues such as ACL, EACL, and EMNLP, where he also regularly serves as a reviewer. His contribution to the Computational Linguistics community extends to co-organizing BlackboxNLP (2023, 2024), a popular workshop focusing on analyzing and interpreting neural networks for NLP, and offering a tutorial at EACL 2024 conference.

Seminar: "Cross-lingual Transfer Learning with Multilingual Masked Language Models"

Fri, 23 Feb 2024 11:00:00 +0000

Invited Speaker: Mamoru Komachi (Hitotsubashi University, Japan)

Bio: He is a Professor at Hitotsubashi University in Japan. His research focuses on language resources and evaluation, NLP applications and cross-lingual NLP.

Seminar: "Mining and Modeling Perspectives in NLP"

Thu, 22 Feb 2024 13:00:00 +0000

Invited Speaker: Valerio Basile (University of Turin, Italy)

Bio: Valerio Basile is an Assistant Professor at the Computer Science Department of the University of Turin, Italy, member of the Content-centered Computing group and the Hate Speech Monitoring group. His work spans across several areas such as: formal representations of meaning, linguistic annotation, natural language generation, commonsense knowledge, semantic parsing, sentiment analysis, and hate speech detection, perspectives and bias in supervised machine learning, from data creation to system evaluation. He is currently PI of the project BREAKhateDOWN “Toxic Language Understanding in Online Communication”, and among the main proponents of the Perspectivist Data Manifesto.

[1] The Perspectivist Manifesto. https://pdai.info/

[2] Basile et al. 2021. We Need to Consider Disagreement in Evaluation

[3] Cabitza et al. AAAI-23. Toward a perspectivist turn in ground truthing for predictive computing

Seminar: "Capture Cognitive Biases: Discount Model and Trustworthiness Evaluation"

Thu, 15 Feb 2024 13:00:00 +0000

Invited Speaker: Hanbyul Song (Cardiff University)

Bio: Dr. Hanbyul Song is a Research Assistant in Cardiff University’s DISINFTRUST project. With a PhD in Linguistics from University College London, her research investigated biases influencing the acquisition of probabilistic morpho-phonological patterns. Her research expands into cognitive psychology, computational modelling, NLP, and language processing, aiming to reveal the complexities of cognitive biases and their implications.

Seminar: "NLP at AMPLYFI: From Raw Text to Actionable Market Reports in One Click"

Thu, 01 Feb 2024 13:00:00 +0000

Invited Speaker: Henrijs Princis (AMPLIFY)

Bio: Henrijs Princis is a machine learning engineer at AMPLYFI. He graduated from Cardiff University, and obtained his Master’s degree from University of Cambridge. He is interested in machine learning and natural language processing, with a particular focus on code synthesis. He’s co-authored a paper on explainable artificial intelligence [1] and his masters thesis explores how to make LLMs more efficient for code generation.

[1] Grange, Jacques A., et al. "XAI & I: Self-explanatory AI facilitating mutual understanding between AI and human experts." Procedia Computer Science 207 (2022): 3600-3607.

Lecturer Positions

Wed, 24 Jan 2024 00:00:00 +0000

The School of Computer Science and Informatics at Cardiff University (Wales, United Kingdom) is now recruiting for Lecturer (~Assistant Prof) posts in several areas of Computer Science, including Natural Language Processing (NLP).

Further details can be found here:

Lecturer (Teaching & Research)

Application Deadline: Sunday, 11 February 2024.

Seminar: "Low-Resource Text Generation: Gaelic, Shared Tasks, and Multitask Learning"

Thu, 14 Dec 2023 13:00:00 +0000

Invited Speaker: David M. Howcroft (Edinburgh Napier University)

Mock Presentations for EMNLP 2023

Thu, 30 Nov 2023 13:00:00 +0000

Invited Speaker: Various CardiffNLP members

Seminar: "Large Language Models and Tabular Data"

Thu, 23 Nov 2023 13:00:00 +0000

Invited Speaker: Jorge Osés (Graphext and University of Jaén, Spain)

Seminar: "Taking Automated Fact-checking to the Real World"

Thu, 16 Nov 2023 13:00:00 +0000

Invited Speaker: Michael Schlichtkrull (University of Cambridge)

Bio:

Michael Schlichtkrull is an affiliated lecturer and postdoctoral research associate at the University of Cambridge, and an incoming lecturer at Queen Mary University of London. He works on automated fact checking and other epistemically complicated NLP problems. He has also worked extensively on graph neural networks for NLP, tackling problems including relational link prediction, question answering, and interpretability. Michael received his PhD from the University of Amsterdam, during the process of which he also spent several years visiting the University of Edinburgh.

Seminar: "Are Emergent Abilities in Large Language Models just In-Context Learning?"

Thu, 09 Nov 2023 13:00:00 +0000

Invited Speaker: Harish Tayyar Madabushi (University of Bath)

Bio:

Dr Tayyar Madabushi’s long term research goals are focused on investigating methods of incorporating high-level cognitive capabilities into models. In the short and medium term, his research is focused on the infusion of world knowledge, common sense and reasoning into pre-trained language models to improve performance on complex tasks such as multi-hop question answering, conversational agents, and social media analysis.

Dr Tayyar Madabushi completed his PhD in AI, focusing on automated question answering at the University of Birmingham in 2019 and began his current post as Lecturer in Artificial Intelligence at the University of Bath in 2022. His research has been influential in the area of combining construction grammar and pre-trained language models, as he conducted the first exploration in this field, paving the way for further developments.

Seminar: "NLP for Corpus Linguistics in Minoritised Contexts: Past, Present and Future Research Projects and Opportunities"

Thu, 02 Nov 2023 13:00:00 +0000

Invited Speaker: Dawn Knight (Cardiff University - ENCAP)

Reading Group: "Probing Pretrained Language Models for Lexical Semantics"

Thu, 28 Sep 2023 13:00:00 +0000

Kiamehr will focus on the following paper (see below) and then we will have time for discussion:

Probing Pretrained Language Models for Lexical Semantics

There is no need to read the paper, but it could be helpful to at least skim through it.

Reading Group: "Bias Benchmarks for Question Answering"

Thu, 21 Sep 2023 13:00:00 +0000

Yi will provide an overview of the topic by focusing on the following papers (see below) and then we will have time for discussion:

There is no need to read the papers, but could be helpful to at least skim through them.

[Internal] Quaterly Group Meeting

Thu, 14 Sep 2023 13:00:00 +0000

Seminar: "Social bias in Embeddings and Masked Language Models"

Thu, 07 Sep 2023 13:00:00 +0000

Invited Speaker: Yi Zhou (Cardiff University - COMSC)

Seminar: "ChatArena: Multi-Agent Language Game Environments for Large Language Models"

Thu, 25 May 2023 13:00:00 +0000

Invited Speaker: Yuxiang Wu (University College London)

Bio: Yuxiang Wu is a final-year PhD student in the Department of Computer Science at University College London (UCL), advised by Prof. Sebastian Riedel and Prof. Pontus Stenetorp. His research mainly focuses on Large Language Models, Question Answering, and Knowledge-augmented Pre-trained Language Models. He has published 12 papers in top AI/NLP conferences and journals (ACL, EMNLP, AAAI, IJCAI, KDD, TACL). His works have been cited by more than 1900 times, and won Best Paper Award AKBC2020, champion of Neurips 2020 EfficientQA Competition, and Best Poster Award ENLSP Workshop in NeurIPS 2022.

Seminar: "Improving Service Quality and Ethnic Inequalities in Health and Social Care"

Thu, 04 May 2023 13:00:00 +0000

Invited Speaker: [Seongsoo (Simon) Jang (Senior Lecturer of Marketing, Cardiff Business School)

Bio: Dr. Jang is a Senior Lecturer of Marketing in Cardiff Business School at Cardiff University. As an interdisciplinary empirical researcher, he does quantitative research on digital marketing, health/sustainability marketing, and tourism analytics by (1) using real-world data collected from two-sided platforms, mobile app operators, and other commercial sources, (2) combining psychology/behavioral theories and advanced methods (hierarchical modeling, text mining, and spatial analytics), and (3) addressing contemporary marketing and business problems. He has published in decent marketing and tourism journals, including Journal of Product Innovation Management, British Journal of Management, Journal of Public Policy and Marketing, Journal of Business Research, Annals of Tourism Research, Tourism Management, Journal of Travel Research, and International Journal of Hospitality

Seminar: "Analysing Adherence to Protective Behaviours over the COVID-19 Pandemic using Twitter and Sentiment Analysis"

Thu, 27 Apr 2023 13:00:00 +0000

Invited Speaker: Tristan Naidoo (Imperial College London)

Seminar: "NLP for Language Teaching and Assessment"

Thu, 20 Apr 2023 13:00:00 +0000

Invited Speaker: Mariano Felice (British Council)

Bio: Mariano Felice is a Senior Researcher and Data Scientist for Language Assessment and Learning at the British Council. His work involves looking at how artificial intelligence (AI) and natural language processing (NLP) can improve computer-assisted learning and testing, from mining datasets and building models to supporting colleagues in the adoption of new technology. Mariano is also a Visiting Researcher at the University of Cambridge, where he was a Research Associate as part of the ALTA Institute. He has a PhD in computer science from the University of Cambridge and has worked extensively on NLP for language learning and assessment, including grammatical error correction, automatic error typing, system evaluation, automatic cloze test generation and item calibration.

New Research Associate (Data Engineer) Position

Tue, 18 Apr 2023 00:00:00 +0000

We are looking for a Research Associate (Data Engineer) for the TweetNLP project, which is funded by EPSRC. TweetNLP is a recently launched platform focused on NLP and its application on social media.

For an informal discussion about the role, please contact Jose Camacho Collados (Senior Lecturer).

Application Deadline: 27 April 2023

Start Date: 1 May 2023 (or soon afterwards)

Discussion: "Impact of ChatGPT on NLP research"

Thu, 30 Mar 2023 13:00:00 +0000

Seminar: "Idiom Processing in Transformer, a Translation Case Study"

Thu, 23 Mar 2023 13:00:00 +0000

Invited Speaker: Verna Dankers (University of Edinburgh)

The talk discusses experiments from the following two articles:

Dankers, V., Bruni, E., & Hupkes, D. (2022, May). The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 4154-4175).
Dankers, V., Lucas, C., & Titov, I. (2022, May). Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 3608-3626).

Seminar: "Representation Learning for Word Senses"

Thu, 16 Mar 2023 13:00:00 +0000

Invited Speaker: Yi Zhou (Cardiff University - COMSC)

Seminar: "Polecat's NLP projects"

Thu, 23 Feb 2023 13:00:00 +0000

Invited Speaker: Alon Samuel and Chris Bowdon (Polecat)

Polecat is a leading reputational intelligence company that helps companies influence their corporate reputation using real-time textual news sources and social media.

Seminar: "Associating Texts with Knowledge Graphs"

Thu, 16 Feb 2023 13:00:00 +0000

Invited Speaker: Hang Dong

References:

[1] Dong, H., Falis, M., Whiteley, W., Alex, B., Matterson, J., Ji, S., … & Wu, H. (2022). Automated clinical coding: what, why, and where we are?. npj digital medicine, 5(1), 159. https://doi.org/10.1038/s41746-022-00705-7

[2] Dong, H., Suárez-Paniagua, V., Whiteley, W., & Wu, H. (2021). Explainable automated coding of clinical notes using hierarchical label-wise attention networks and label embedding initialisation. Journal of Biomedical Informatics, 116, 103728. https://arxiv.org/abs/2010.15728

Seminar: "Towards compute efficient large language models"

Thu, 09 Feb 2023 13:00:00 +0000

Invited Speaker: Nikos Aletras

Seminar: "What Is Needed Vs What is Built in NLP: Toxic Language Detection and Automated Fact-checking Models As Use Cases"

Thu, 26 Jan 2023 13:00:00 +0000

Invited Speaker: Nedjma Ousidhoum

Enabling Early Health Care Intervention by Detecting Depression in Users of Web-Based Forums using Language Models: Longitudinal Analysis and Evaluation

Sun, 01 Jan 2023 00:00:00 +0000

Negativity spreads faster: A large-scale multilingual twitter analysis on the role of sentiment in political communication

Sun, 01 Jan 2023 00:00:00 +0000

Seminar: "Social Media and Crowdsourcing Platforms in Disaster Management"

Thu, 01 Dec 2022 13:00:00 +0000

Invited Speaker: Diana Contreras Mojica

A Benchmark for Neural Readability Assessment of Texts in Spanish

Thu, 01 Dec 2022 00:00:00 +0000

Generative Language Models for Paragraph-Level Question Generation

Thu, 01 Dec 2022 00:00:00 +0000

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Thu, 01 Dec 2022 00:00:00 +0000

Improving Embeddings Representations for Comparing Higher Education Curricula: A Use Case in Computing

Thu, 01 Dec 2022 00:00:00 +0000

Probing Relational Knowledge in Language Models via Word Analogies

Thu, 01 Dec 2022 00:00:00 +0000

TweetNLP: Cutting-Edge Natural Language Processing for Social Media

Thu, 01 Dec 2022 00:00:00 +0000

Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts

Tue, 01 Nov 2022 00:00:00 +0000

Neural Readability Pairwise Ranking for Sentences in Italian Administrative Language

Tue, 01 Nov 2022 00:00:00 +0000

Cardiff NLP Hackathon 2022

Thu, 20 Oct 2022 00:00:00 +0000

📅 16th and 17th Nov, 10am - 5pm

📍 Tramshed Tech

Seminar: "TempoWiC: An Evaluation Benchmark for Detecting Meaning Shift in Social Media"

Thu, 13 Oct 2022 13:00:00 +0000

Invited Speaker: Daniel Loureiro

Related Links:

Seminar: "Federated Learning for Exploiting Annotator Disagreements in NLP"

Thu, 06 Oct 2022 13:00:00 +0000

Invited Speaker: Nuria Rodríguez Barroso

TempoWiC: An Evaluation Benchmark for Detecting Meaning Shift in Social Media

Sat, 01 Oct 2022 00:00:00 +0000

Twitter Topic Classification

Sat, 01 Oct 2022 00:00:00 +0000

Conference-like Presentations

Thu, 29 Sep 2022 13:00:00 +0000

[Internal] Quaterly Group Meeting

Thu, 22 Sep 2022 13:00:00 +0000

14 New Lecturer/Senior Lecturer Positions

Fri, 09 Sep 2022 00:00:00 +0000

The School of Computer Science and Informatics at Cardiff University (Wales, United Kingdom) is now recruiting for 14 posts at the levels of Lecturer (~Assistant Prof) or Senior Lecturer (~Associate Prof) in several areas of Computer Science, including Natural Language Processing (NLP).

Further details can be found here:

Application Deadline: Friday, 7 October 2022.

[Internal] Cardiff NLP Hackathon Organisation

Thu, 08 Sep 2022 13:00:00 +0000

New Research Associate Position

Thu, 11 Aug 2022 00:00:00 +0000

We are looking for a Research Associate for a UKRI Future Leaders Fellowship project on Natural Language Processing titled ‘‘Unsupervised background knowledge for language understanding’’.

For an informal discussion about the role, please contact Jose Camacho Collados (Senior Lecturer) – camachocolladosj@cardiff.ac.uk.

Application Deadline: September 4th

Start Date: January 2023 (flexible)

New Teaching Associate Position

Thu, 11 Aug 2022 00:00:00 +0000

Applications are invited for nine Teaching Associate posts in the School of Computer Science & Informatics at Cardiff University. Posts are available on a part-time (0.5FTE) basis. Part-time posts will be accompanied with the opportunity to also study towards a PhD part-time.

For an informal discussion about the role please contact Dr Martin Chorley - ChorleyMJ@cardiff.ac.uk

Application Deadline: September 7th

Conference-like Presentations

Tue, 05 Jul 2022 13:00:00 +0000

Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences

Fri, 01 Jul 2022 00:00:00 +0000

CardiffNLP-Metaphor at SemEval-2022 Task 2: Targeted Fine-tuning of Transformer-based Language Models for Idiomaticity Detection

Fri, 01 Jul 2022 00:00:00 +0000

PCL Detection

Tue, 28 Jun 2022 00:00:00 +0000

TempoWiC

Tue, 28 Jun 2022 00:00:00 +0000

Tweet NLP

Tue, 28 Jun 2022 00:00:00 +0000

New Research Assistant Position

Mon, 27 Jun 2022 00:00:00 +0000

We are looking for a Research Assistant for a UKRI Future Leaders Fellowship project on Natural Language Processing.

For an informal discussion about the role, please contact Jose Camacho Collados (Senior Lecturer) – camachocolladosj@cardiff.ac.uk.

Application Deadline: July 11th

Start Date: September 2022 or later (flexible)

[Internal] Cardiff NLP Workshop Organisation

Thu, 23 Jun 2022 13:00:00 +0000

Seminar: "Textual Complexity is in the Eye of the Beholder"

Thu, 09 Jun 2022 13:00:00 +0000

Invited Speaker: Sian Gooding

Short Bio: Sian Gooding is a PhD student at the University of Cambridge Computer Laboratory within the Natural Language and Information Processing group and a visiting researcher at the Language, Computation and Cognition Lab. Her research focuses on readability and text simplification – the study of how to automatically adapt text to suit the needs of different audiences.

PeruSIL: A Framework to Build a Continuous Peruvian Sign Language Interpretation Dataset

Wed, 01 Jun 2022 00:00:00 +0000

Simple TICO-19: A Dataset for Joint Translation and Simplification of COVID-19 Texts

Wed, 01 Jun 2022 00:00:00 +0000

Towards Readability-Controlled Machine Translation of COVID-19 Texts

Wed, 01 Jun 2022 00:00:00 +0000

XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond

Wed, 01 Jun 2022 00:00:00 +0000

Seminar: "Quantifying Synthesis and Fusion and their Impact on Machine Translation"

Thu, 19 May 2022 13:00:00 +0000

Invited Speaker: Arturo Oncevay

Short Bio: Arturo Oncevay (he/him) is a PhD candidate at the University of Edinburgh, Scotland. He was a member of the Artificial Intelligence group at the Pontificia Universidad Católica del Perú (PUCP, Peru), where he graduated from Informatics Engineering and Masters in Computer Science. His work focuses on low-resource machine translation and in computational typology for NLP, and he likes to support the development of NLP tools for endangered languages spoken in the Amazonia. He has also co-organised the AmericasNLP workshop (NAACL 2021) and shared task on machine translation (NAACL 2021) and speech-to-text translation (in preparation for NeurIPS 2022).

Seminar: "Language Models for Social Media: Challenges and Applications"

Thu, 12 May 2022 13:00:00 +0000

Expressions of Interest for Cardiff NLP Summer Workshop 2022

Wed, 11 May 2022 00:00:00 +0000

We are happy to officially announce the 1st Cardiff NLP Summer Workshop on June 30 and July 1!

This workshop will be an opportunity for participants to interact and attend talks/tutorials from high-profile NLP researchers from industry and academia.

Registration is free. Submit your Expression of Interest by May 30. More information here.

TimeLMs: Diachronic Language Models from Twitter

Sun, 01 May 2022 00:00:00 +0000

[Internal] Cardiff NLP Workshop Organisation

Thu, 28 Apr 2022 13:00:00 +0000

[Internal] New NLP PhD/RA Office Allocations

Thu, 21 Apr 2022 13:00:00 +0000

5-minute Presentations

Thu, 07 Apr 2022 13:00:00 +0000

Hands-on Class with 🤗: How to Build Machine Learning Collaboratively?

Thu, 31 Mar 2022 13:00:00 +0000

Speaker: Thomas Simonini (Machine Learning Engineer at HuggingFace)

Description of the Session:

How can you show what a Machine Learning model does once it’s trained?

In this talk, you’re going to learn how to create Machine Learning apps and demos using Streamlit and Gradio, Python libraries for this purpose. Additionally, you’ll see how to share them with the rest of the Open Source ecosystem. Learning to create graphic interfaces for models is extremely useful for sharing with other people interesting them.

What is required to follow it?

👉 Basic knowledge of Python

👉 Conceptual knowledge of ML

👉 A google Colab account

👉 A Hugging Face Hub account

Hugging Face organization page for the tutorial: https://huggingface.co/CardiffNLPTutorialHF (anyone can request to join)

Zoom Link: https://cardiff.zoom.us/j/81951311481?pwd=WkJsN09XZ01OM09KaGsvNEx1SVEvUT09

[Internal] Cardiff NLP Workshop Organisation

Thu, 24 Mar 2022 13:00:00 +0000

Seminar: "Morphological Regularities in English Word Formation: Perspectives for Further Development"

Thu, 17 Mar 2022 13:00:00 +0000

1st Cardiff NLP Summer Workshop

Thu, 10 Mar 2022 00:00:00 +0000

We are organising a free in-person 2-day Natural Language Processing workshop in Cardiff from June 30 to July 1. We will have invited speakers, tutorials, networking, etc.

More information coming soon! For now, safe the date!

1st Cardiff NLP Summer Workshop

Tue, 08 Mar 2022 00:00:00 +0000

We are organising a free in-person workshop on Natural Language Processing.

It will take place from June 30th to July 1st 2022 in Abacws, the brand-new building for the School of Computer Science and the School of Mathematics at Cardiff University.

Target Audience

The workshop is especially intended to PhD students in UK/Europe, but everyone would be welcome!

Workshop Activities

Invited speakers
Tutorials
Networking

And of course you will have the chance to visit our lovely city while in Cardiff!

More details here!

5-minute Presentations

Thu, 03 Mar 2022 13:00:00 +0000

Hypernym Discovery

Fri, 18 Feb 2022 21:27:12 +0000

T-NER

Fri, 18 Feb 2022 21:26:01 +0000

Don't Patronize Me!

Fri, 18 Feb 2022 21:25:57 +0000

TimeLMs

Fri, 18 Feb 2022 21:25:57 +0000

RELATIVE

Fri, 18 Feb 2022 21:25:48 +0000

Meemi

Fri, 18 Feb 2022 21:25:44 +0000

TweetEval

Fri, 18 Feb 2022 21:25:38 +0000

SeVeN: Semantic Vector Networks

Fri, 18 Feb 2022 21:24:59 +0000

Looking for PhD Students!

Fri, 18 Feb 2022 00:00:00 +0000

Do you aim to make information more accessible to everyone? I am looking for students to work on different tasks for text adaption (e.g. Text Simplification, Readability Assessment, etc.).

You could either apply to one of the School of Computer Science studentships (Deadline 29/04), or be self-funded. Do not hesitate to get in touch if you’re interested!

[Internal] Quarterly Group Meeting

Thu, 17 Feb 2022 13:00:00 +0000

Reading Group: "Sentiment Analysis and COVID-19"

Thu, 10 Feb 2022 13:00:00 +0000

[Internal] Staff Meeting

Thu, 03 Feb 2022 13:00:00 +0000

Reading Group: "Interpretability in NLP"

Thu, 27 Jan 2022 13:00:00 +0000

LMMS reloaded: Transformer-based sense embeddings for disambiguation and beyond

Sat, 01 Jan 2022 00:00:00 +0000

Seminar: "Learning Text Representations from Pre-trained Language Models via Contrastive Learning and Self-Distillation"

Thu, 02 Dec 2021 13:00:00 +0000

Conference-like Presentations

Thu, 25 Nov 2021 13:00:00 +0000

Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction

Mon, 01 Nov 2021 00:00:00 +0000

Distilling Relation Embeddings from Pretrained Language Models

Mon, 01 Nov 2021 00:00:00 +0000

On the Cross-lingual Transferability of Contextualized Sense Embeddings

Mon, 01 Nov 2021 00:00:00 +0000

Discussion Panel: "Teaching in NLP"

Thu, 28 Oct 2021 13:00:00 +0000

Seminar: "A Medley of Event-Based Modality and Role Question Generation"

Thu, 14 Oct 2021 13:00:00 +0000

Seminar: "Multilingual Machine Translation with Language-Specific Encoder-Decoders: Translation Quality and Gender Accuracy"

Thu, 23 Sep 2021 13:00:00 +0000

Short Presentations by PhD Students

Thu, 16 Sep 2021 13:00:00 +0000

Seminar: "Graphext, a tool for exploring and modeling complex datasets of structured and unstructured data"

Thu, 09 Sep 2021 13:00:00 +0000

BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?

Sun, 01 Aug 2021 00:00:00 +0000

COVID-19 and Misinformation: A Large-Scale Lexical Analysis on Twitter

Sun, 01 Aug 2021 00:00:00 +0000

Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection

Sun, 01 Aug 2021 00:00:00 +0000

Probing Pre-Trained Language Models for Disease Knowledge

Sun, 01 Aug 2021 00:00:00 +0000

Analysis and Evaluation of Language Models for Word Sense Disambiguation

Tue, 01 Jun 2021 00:00:00 +0000

Evaluating Language Models for the Retrieval and Categorization of Lexical Collocations

Thu, 01 Apr 2021 00:00:00 +0000

T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition

Thu, 01 Apr 2021 00:00:00 +0000

WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context

Thu, 01 Apr 2021 00:00:00 +0000

A Mixture-of-Experts Model for Learning Multi-Facet Entity Embeddings