After years in preprint, our paper is finally out! We introduce LambdaG, a simple new authorship verification method that matches complex neural approaches. This supports the theory of grammar as a behavioural biometric (like a signature or gait). www.nature.com/articles/s41... #nlp #llm #forensic
Well-known #forensic #linguistics cases involved impersonation, e.g. murderer pretending to be the victim in text messages. In a new preprint with Baoyi Zeng we show that #LLMs can't fool authorship verification methods via prompting alone. Paper on arXiv: https://arxiv.org/abs/2603.29454
My #RStats package for forensic authorship analysis, 'idiolect', now has an associated paper published in the Journal of Open Source Software: https://doi.org/10.21105/joss.07575 New release of idiolect, 1.2.0, also available from #CRAN.
#forensic #linguistics
Just published in JOSS: 'idiolect: An R package for forensic authorship analysis' https://doi.org/10.21105/joss.07575
Opportunity for a PhD candidate in English linguistics. Please repost.
jobs.unibas.ch/offene-stell...
🎉 NEW PAPER with @gsakr.bsky.social
"Multivariate Analyses of Tongue Contours from Ultrasound Tongue Imaging"
👅📡🩻📉
doi.org/10.1177/0023...
Out in Evolutionary Human Sciences! With @mikekestemont.bsky.social, @jbcamps.bsky.social, @remcosleiderink.bsky.social & Anne Chao
New work on unseen species models for cult heritage to the question: how many stories were _shared_ between medieval French and Dutch literature?
lnkd.in/exyAWtir
: Save the date! IAFLL Porto 2027.
12-16 July 2027, at the Faculty of Arts and Humanities (FLUP) of the Universidade do Porto. Até já!
youtu.be/LaJn_I7YzB8?...
Consider a noun phrase formed by a noun, an adjective, a numeral and a demonstrative. There are 24 possible orders but only some of them have been attested when examining the preferred order in world languages. Some researchers hypothesize that there is a hard constraint banning certain orders.
My latest paper with Hugo Bowles and Claire Wood examines a Dickens mystery: did he author the recently decoded story “The Two Brothers”? The answer is complicated. The paper showcases our new method, LambdaG (forthcoming!).
Delighted to announce this book is finally being published! Over 3 years in the production. I've written Chapter 3 - Ethics and Professional Conduct Oversight in Forensic Linguistic Expert Evidence.
#ForensicLinguistics #Ethics #ExpertEvidence
What an absolute pleasure it was to attend the 6th edition of CHR! Huge thanks to everyone who helped make this edition even better than the last #CHR2025 Onward to Manchester, home of some wonderful computing history:
www.atlasobscura.com/articles/com...
We’ll do our best! 😀
Congratulations!
Thanks, @jtauber.com! Very interesting.
How good are LLMs at identifying and tagging metaphors in text? Turns out, pretty good!
In our new study, we ask 10 different open- and closed-source LLMs to label all metaphorical expressions in a dataset of film reviews using <Metaphor> and </Metaphor> XML tags.
arxiv.org/abs/2509.24866
The Derek Bentley Case 👇
In a gripping two-part series, the Writing Wrongs podcast investigates one of the UK’s most infamous miscarriages of justice: the tragic story of Derek Bentley, who was sentenced to death in 1953.
If you're attending Konvens 2025 at Hildesheim, don't miss our tutorial on Reading Concordances with Algorithms tomorrow, where we talk about our mathematical framework and given some background on the FlexiConc library. konvens-2025.hs-hannover.de/program/#fle... @rc21project.bsky.social
📢 Season 2 of Writing Wrongs kicks off tomorrow! 📢
The first episode is a two-parter exploring the classic case of #DerekBentley.
We're joined by Prof. Malcolm Coulthard whose analysis contributed to Derek's posthumous acquittal.
Listen wherever you get your podcasts!
Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: web.stanford.edu/~jurafsky/sl...
Pat Strycharczuk will be presenting our paper at #Interspeech2025 on Wednesday afternoon (A02-O6), where we applied forensic speaker comparison methods to ultrasound tongue imaging data to think about the individuality of articulatory strategy
📄 www.isca-archive.org/interspeech_...
Super excited to share our new multimodal corpus analysis, "Iconic Words Are Associated With Iconic Gestures" 🥳
Project led by our PhD student Ell Wilding and in collab w/ @jeannettel.bsky.social & @mperlman.bsky.social:
doi.org/10.1111/cogs...
Some days my working day is: fix OneDrive sync issues. It has one job and it fails completely at that. All other cloud systems can sync things perfectly. Unbelievable.
📢📃 New open access 🔓 paper with @perez-paredes.bsky.social in @registerstudies.bsky.social: Exploring public-oriented research communication - A register perspective. You can find the paper here: doi.org/10.1075/rs.2... & some details in the 🧵 below⬇️ @mcrlinguistics.bsky.social @um.es
🔊 Dropping this Friday, the Series 1 finale of Writing Wrongs, the AIFL podcast! 🔊
@timgrant123.bsky.social and @drniccimacleod.bsky.social will be answering some of the questions that have come in from listeners over the course of the past 7 episodes 👇👇👇
On Monday, Dr James Tompkinson (University of York) and I presented this paper at the IAFPA 2025 conference, where we showed preliminary results of applying authorship analysis techniques to transcribed speech. You can find the slides at the link below.
Abstract and slides for my #DH2025 talk "Examining an author’s individual grammar" can now be found on my website below. This also includes a tutorial to use LambdaG to study authors' idiosyncratic grammar patterns.
That's often the case anyway! 😄
Have you tried using ChatGPT or similar? I tend to use LLMs only for things like this where the output is verifiable. If the problem has been encountered before many times it's quite reliable.
