I'll be presenting some of the recent research coming out of the @techwolfbe research team at the @RecSysHR workshop at @ACMRecSys in Seattle next week. It's about "one little trick" that considerably improves skill extraction results!
#RecSys2022
Next up: @JensJorisDC presenting joint work from @techwolfbe and @ResearchUGent: "Career Path Prediction using Resume Representation Learning and Skill-based Matching," get the preprint here: https://t.co/HCqJvQN35x
We published the list of accepted @RecSysHR papers! This year we have a program with 10 paper presentations, topics ranging from skill extraction, CV parsing, career path prediction, and more. Congrats to all authors, and thanks to our PC for reviewing! https://t.co/3m0LY1QbBh
Decided to pick the best possible time, the start of ACL, to have a totally-not-ACL-related new pre-print out! Still an early approach, the work uses LLMs at both ends of the pipeline (data gen + re-ranking) for zero-shot ESCO skills identification https://t.co/KPNWvXPwrF
This is a highly relevant article for the scarce domain of job market understanding in NLP. Nevertheless, it seems to be missing some related works from 2022 (and before) regarding Occupational Skill Extraction or Classification (though not graph-based). To name a few:
(1/7) 🧵
👀Sneak peek of a weekend project I'm working on: intuitive video editing via language. I hope to add many NLP-based features soon that will allow for insanely quick text-based video editing, without ever opening actual editing software.
Potentially nitpicky but competitive advantage in AI goes not so much to those with data but those with a data engine: iterated data aquisition, re-training, evaluation, deployment, telemetry. And whoever can spin it fastest. Slide from Tesla to ~illustrate but concept is general
Today Sofie Labat presented research on the detection of Emotion Trajectories in Dutch Customer Service Dialogues @WNUT workshop @coling2022. More info in https://t.co/fDYAAxQBFe @thomeestr@ugentnlp
We have published the full recording of our @RecSysHR 2022 Workshop, held at @ACMRecSys 2022, last month in Seattle! ▶️ See the recording here: https://t.co/sb7CPOznXN.
Our program includes two keynotes (@indeed & @hongliangjie@LinkedIn's), a panel (with a.o., @ChaToX), and...
That's a wrap! We loved this 2nd edition of our @RecSysHR workshop! Thanks to all presenters, keynote speakers (@hongliangjie, Robyn Rap), panelists (Helen Hulsker, @ChaToX) and attendees for making this edition a success! Who knows, perhaps we meet in Singapore 😊 #RecSys2022
Stepping in to the #recsys2022 conference as an NLP researcher I was expecting to miss out on a lot of background knowledge. Couldn't be more wrong, with many of the papers using Transformer models, this feels very familiar! Getting some refreshing views on our #NLProc models 🤩
Had a blast with the @techwolfbe research team at the #taw2022 workshop in Amsterdam. Props to the @ZetaVector team for organizing such an interesting event, with a great combination of academic and industrial insights. We'll be back!
We have published the pre-prints of the accepted papers at our workshop! Linked for your convenience at https://t.co/k5sYROp5Bl and in our (preliminary) program: https://t.co/WeoUoJsIgp.
Hope to see you next week at #RecSys2022! @ACMRecSys
I'll be presenting some of the recent research coming out of the @techwolfbe research team at the @RecSysHR workshop at @ACMRecSys in Seattle next week. It's about "one little trick" that considerably improves skill extraction results!
#RecSys2022
Finally, to stimulate research on automated skill extraction, we release our development and test data, which is constructed on top of the “SkillSpan” dataset by @mjjzha et al., adding #ESCO skill labels to the spans.
https://t.co/UHEFFfJS7L