[A stylized clam.]

Computational
Linguistics
at
Manitoba

About CLAM

The Computational Linguistics at Manitoba (CLAM) Lab advances research at the confluence of artificial intelligence and linguistics:

  • We develop digital tools, methods, and resources that help linguists develop and test linguistic theories.
  • We develop natural language processing systems that help digital humanists and computational social scientists make sense of large, unstructured text collections.
  • We develop interactive language technology that supports the work of writers, translators, and other professional knowledge workers.

Team

Faculty

Students

Alumni

Luke Wiebe
Undergraduate Research Assistant

Partnerships

The Lab maintains close working relationships with the Austrian Research Institute for Artificial Intelligence (OFAI) and the Semantic Artificial Intelligence and Creativity Laboratory (SAICL) at East Texas A&M University.

Interested in joining our team? We are currently offering funded PhD positions for research topics in computational humour, historical born-digital corpora, and Indigenous language technology.

News

JOKER Lab at CLEF 2026

Workshop on humour in the machine

EJHR call for papers

Special issue "AI Meets Humour"

Can LLMs learn humour?

Tristan Miller in Smithsonian Magazine

BDCAM25 panel convened

Usenet as an archive of digital discourse

CHum proceedings published

Workshop on computational humour

Can AI create humour?

PunCAT featured on ORF Ö1

Early Career Researcher Day

Opportunities, challenges of AI in research

Canada's Innovation Leaders article

AI brings cultural nuances to humour

UM Linguistics colloquium

Computational processing of wordplay

Austrian public radio interview

Tristan Miller on AI in education

Featured publications

Liana Ermakova, Igor Kuzmin, Poojan Vachharajani, Tristan Miller, Anne-Gwenn Bosser, and Jaap Kamps.
CLEF 2026 JOKER track: Humour detection, search, and translation.
In Ricardo Campos, Adam Jatowt, Yanyan Lan, Mohammad Aliannejadi, Christine Bauer, Sean MacAvaney, Avishek Anand, Zhaochun Ren, Suzan Verberne, Nan Bai, and Masoud Mansoury, editors, Advances in Information Retrieval: 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29–April 2, Proceedings, Part IV, volume 16486 of Lecture Notes in Computer Science (ISSN 0302-9743), pages 242–250, Cham, Switzerland, March 2026. Springer. ISBN 978-3-032-21320-4. DOI: 10.1007/978-3-032-21321-1_34.
Over the last few years, the JOKER Track has created an active community of researchers in NLP and IR working together on the non-literal use of language in text—which is still challenging for both AI models and humans, as it requires understanding implicit cultural references and double meanings. Its benchmarks on humorous text analysis, retrieval, and translation have become standard references. We made significant changes to the track's setup and tasks in 2024 and 2025, and propose continuing these to complete the test collections. The CLEF 2026 JOKER track will contain the following four tasks. Task 1 (Humor-aware Information Retrieval): retrieve short humorous texts for a query. Task 2 (Pun Translation): translate puns from English to French and Spanish. Task 3 (Onomastic Wordplay Translation): translate onomastic wordplay from English to French. Task 4 (Humor Generation): guided creativity.
@inproceedings{ermakova2026clef,
author       = {Liana Ermakova and Igor Kuzmin and Poojan Vachharajani and Tristan Miller and Anne-Gwenn Bosser and Jaap Kamps},
editor       = {Ricardo Campos and Adam Jatowt and Yanyan Lan and Mohammad Aliannejadi and Christine Bauer and Sean MacAvaney and Avishek Anand and Zhaochun Ren and Suzan Verberne and Nan Bai and Masoud Mansoury},
title        = {{CLEF} 2026 {JOKER} Track: Humour Detection, Search, and Translation},
booktitle    = {Advances in Information Retrieval: 48th {European} {Conference} on {Information} {Retrieval}, {ECIR}~2026, {Delft}, {The} {Netherlands}, {March}~29–{April}~2, Proceedings, Part~{IV}},
volume       = {16486},
pages        = {242--250},
series       = {Lecture Notes in Computer Science},
month        = mar,
year         = {2026},
publisher    = {Springer},
address      = {Cham, Switzerland},
isbn         = {978-3-032-21320-4},
issn         = {0302-9743},
doi          = {10.1007/978-3-032-21321-1_34},
}

Punning is a form of humorous wordplay based on semantic ambiguity between two phonologically similar words – the pun and the target – in a context where both meanings are more or less acceptable. While the pun is expressed explicitly, the target is invoked implicitly in the text. Previous work has attempted to quantify and compare phonological features of puns and their targets, looking at correlations with the understandability of the jokes in which they occur. Our study quantifies the phonological distance between pun and target words and assesses possible correlations with funniness ratings of the corresponding jokes. Our statistical analyses on a large dataset of puns reveal a significant negative correlation between phonological distance and perceived funniness for two of the four phonological distance measures we applied. This finding supports the hypothesis, often (implicitly) made in previous research but never verified at this scale, that lower phonological distance between a pun and its target is associated with higher funniness ratings. The parameters of our study suggest that future work should examine the semantic features of pun and target in order to create a more holistic understanding of what contributes to the perceived funniness of punning jokes.
@article{palmann2025whats,
author       = {Anna Palmann and Tristan Miller},
title        = {What's in a Pun? Assessing the Relationship Between Phonological Distance and Perceived Funniness of Punning Jokes},
journal      = {Humor: International Journal of Humor Research},
volume       = {38},
number       = {4},
pages        = {643--658},
year         = {2025},
issn         = {0933-1719},
doi          = {10.1515/humor-2024-0060},
}

Wei Zhao, Jennifer D'Souza, Steffen Eger, Anne Lauscher, Yufang Hou, Nafise Sadat Moosavi, Tristan Miller, and Chenghua Lin, editors.
Proceedings of the First Workshop on Human–LLM Collaboration for Ethical and Responsible Science Production (SciProdLLM).
Association for Computational Linguistics, Kerville, TX, December 2025. ISBN 979-8-89176-307-4.
Large language models (LLMs) are on the rapid rise to empower human researchers in science production at all stages, from the initial conception of research problems to reporting scientific discoveries. In 2025, American publisher Wiley surveyed 5,000 researchers across 70 countries and found that majority support LLM adoption in scientific production. While LLMs could enable faster, cost-effective research addressing global challenges, they raise ethical and trust concerns. To explore these issues, we organized the SciProdLLM workshop with the goal of proving a forum for presenting and discussing research on integrating LLMs into the typical research workflow: from ideation to experimentation to scientific writing, with a particular focus on human-centered approaches that ensure ethical and responsible use of LLMs. We also invite work that evaluates the quality of LLM-assisted research workflows and the resulting outputs.
@book{zhao2025first,
editor       = {Wei Zhao and Jennifer D'Souza and Steffen Eger and Anne Lauscher and Yufang Hou and Nafise {Sadat Moosavi} and Tristan Miller and Chenghua Lin},
title        = {Proceedings of the First Workshop on Human--{LLM} Collaboration for Ethical and Responsible Science Production ({SciProdLLM})},
month        = dec,
year         = {2025},
publisher    = {Association for Computational Linguistics},
address      = {Kerville, TX},
isbn         = {979-8-89176-307-4},
}

Steffen Eger, Yong Cao, Jennifer D'Souza, Andreas Geiger, Christian Greisinger, Stephanie Gross, Yufang Hou, Brigitte Krenn, Anne Lauscher, Yizhi Li, Chenghua Lin, Nafise Sadat Moosavi, Wei Zhao, and Tristan Miller.
Transforming science with large language models: a survey on AI-assisted scientific discovery, experimentation, content generation, and evaluation.
ArXiv e-prints, 2502.05151, February 2025. DOI: 10.48550/arXiv.2502.05151.
With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. Recently, a plethora of new AI models and tools has been proposed, promising to empower researchers and academics worldwide to conduct their research more effectively and efficiently. This includes all aspects of the research cycle, especially (1) searching for relevant literature; (2) generating research ideas and conducting experimentation; generating (3) text-based and (4) multimodal content (e.g., scientific figures and diagrams); and (5) AI-based automatic peer review. In this survey, we provide an in-depth overview over these exciting recent developments, which promise to fundamentally alter the scientific research process for good. Our survey covers the five aspects outlined above, indicating relevant datasets, methods and results (including evaluation) as well as limitations and scope for future research. Ethical concerns regarding shortcomings of these tools and potential for misuse (fake science, plagiarism, harms to research integrity) take a particularly prominent place in our discussion. We hope that our survey will not only become a reference guide for newcomers to the field but also a catalyst for new AI-based initiatives in the area of “AI4Science”.
@article{eger2025transforming,
author       = {Steffen Eger and Yong Cao and Jennifer D'Souza and Andreas Geiger and Christian Greisinger and Stephanie Gross and Yufang Hou and Brigitte Krenn and Anne Lauscher and Yizhi Li and Chenghua Lin and Nafise Sadat Moosavi and Wei Zhao and Tristan Miller},
title        = {Transforming Science with Large Language Models: a Survey on {AI}-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation},
journal      = {{ArXiv} e-prints},
volume       = {2502.05151},
month        = feb,
year         = {2025},
doi          = {10.48550/arXiv.2502.05151},
}