Urja Khurana

Super excited to be presenting our paper "Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?" at #COLM24 during the first poster session on Monday! ✨ arxiv.org/abs/2408.14141 If you are at COLM, I hope to see you at our poster!

Should WOAH start a mentorship programme? 🤔 As the workshop grows, reviewer expectations are rising. We don’t want contributors from adjacent communities penalised by *CL norms. Senior PhDs and beyond could be mentors. Share your thoughts: 👉 forms.gle/safif3rU2rs5S6…

@PranavVenkit Congratulations Pranav! 🎉

✨Looking forward to presenting our paper “DefVerify: Do Hate Speech Models Reflect Their Dataset’s Definition?” at #COLING2025! ✨ aclanthology.org/2025.coling-ma… work done with @eric_nalisnick @antske I hope to see you at our poster at the virtual session at 16.00 CET today! 🎤

I will be presenting our work: OATH-Frames, next week at #EMNLP2024 in Computational Social Science and Cultural Analytics 2 (10:30-12pm EST) Thursday 11/14. Please reach out if you want to chat about NLP x Computational Social Science and LLMs for social good applications ✨

Today @COLM_conf I will present "MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs", our work on comparing stereotypes in generative LLMs across languages. Hope to see you at 4:30 pm at poster #42! #colm2024 arxiv.org/pdf/2406.07243…

This work is a result of my inspiring summer visit to DILL lab last year and collaboration with @swabhz I learned so much during my visit and met great people! work also done with @antske @eric_nalisnick

Super excited to be presenting our paper "Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?" at #COLM24 during the first poster session on Monday! ✨ arxiv.org/abs/2408.14141 If you are at COLM, I hope to see you at our poster!

@dnnslmr Congrats Dennis!!

Wait, that’s me!

🧐 Curious about diverse, human-centered perspectives on cross-lingual models? Join the HumanCLAIM workshop ✨ 📆 11 Jan ‘24 📍Amsterdam We'll dive into boosting diversity in language technology! 🔗clap-lab.github.io/workshop

Just watched @l__kra deliver a great presentation at the Workshop on Multimodal, Multilingual Natural Language Generation @WebNLG #nlg #LLM #MMNLG

The deadline for application is approaching ⏰. If you are interested in #GenerativeAI, do apply for Generative Modeling Summer School #GeMSS23 organized by @jmtomczak, @jesfrellsen, and @pamattei . For more details check out gemss.ai.

Had a great time presenting my work (w @PiaSommerauer & @PiekVossen) on list verbalisations in knowledge graph QA systems at #KGSum! If you're interested how context and pragmatics should influence summarisation and verbalisation it's soon to appear in the workshop proceedings!

This is us!! 🙌 @myrthereuver @urjakh @l__kra @Sel_Baez

We're hiring! Are you an enthusiastic #NLProc researcher and ready for a tenure track? Come and join us at @CLTLVU! workingat.vu.nl/ad/tenure-trac…

@c3K @WOAHWorkshop Yes, looks really relevant, would love to discuss!

@urjakh @WOAHWorkshop Awesome paper, thanks for sharing. This is highly related to our work on a continuous measure of hate speech, not sure if you've run into it before: arxiv.org/abs/2009.10277 - maybe we could discuss sometime. We posted our data on hatespeechdata.com only recently

Had a great time interacting with other researchers at #NAACL2022 last week and chatting about the topics in NLP that I am so passionate about! Also really enjoyed presenting and discussing our poster on hate speech definitions @WOAHWorkshop #NLProc

If you are attending NAACL, I would love to have a chat! (online or in-person)

Additionally, we provide an overview of English hate speech datasets based on the criteria and aim to extend this to other languages in the future as well!

Looking forward to present our work @WOAHWorkshop at #NAACL2022 in-person: "Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions" (arxiv.org/abs/2206.15455) work done w/ Ivar Vermeulen, @eric_nalisnick, Marloes van Noorloos & @antske