@urjakh Profile picture

Urja Khurana

@urjakh

PhD student @CLTLVU. MSc AI @UvA_amsterdam. Working on NLP & ML; robustness, generalization, interpretability, and hate speech.

Joined January 2021
Similar User
Michiel van der Meer photo

@mtichiel

Oskar van der Wal photo

@oskarvanderwal

Arianna Bisazza photo

@AriannaBisazza

Dennis Ulmer 🦋 photo

@dnnslmr

Raquel Fernández photo

@raquel_dmg

Laura Vásquez-Rodríguez photo

@lmvasquezr

Bill Yuchen Lin 🤖 photo

@billyuchenlin

Jaap Jumelet photo

@JumeletJ

SpeechBrain photo

@SpeechBrain1

Xin Eric Wang photo

@xwang_lk

Wei-Ning Hsu photo

@mhnt1580

Diyi Yang photo

@Diyi_Yang

Maartje ter Hoeve photo

@maartjeterhoeve

Sandro Pezzelle photo

@sandropezzelle

Mike Zhang 🦋 photo

@mjjzha

Pinned

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


Urja Khurana Reposted

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 ✨

📢 Can LLMs 🤖 assist social workers 👩🏻‍💻 in characterizing discourse on social issues? We introduce OATH-Frames: a resource for understanding Online Attitudes Towards Homelessness at scale, built with LLMs as assistants. 📄arxiv.org/abs/2406.14883 🔗dill-lab.github.io/oath-frames/ [1/n]

Tweet Image 1


Urja Khurana Reposted

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…


Urja Khurana Reposted

🧐 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


Urja Khurana Reposted

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

Tweet Image 1

Urja Khurana Reposted

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.


Urja Khurana Reposted

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!

Lea Krause proposes "More Informative List Verbalisations". #iswc_conf #iswc2022

Tweet Image 1
Tweet Image 2
Tweet Image 3


Urja Khurana Reposted

Me: 🤔"Shall I put sparkles on it?" Fellow PhD @urjakh , hard at work, not knowing what I'm talking about, responds without looking up: "yes!". This is why you need a supportive PhD friend in your lab. 😎✨


Urja Khurana Reposted

Of course, before I forget, many congrats to CLTeamL🥇in Task A (runner-up🥈: AXiS@UniEd), and NLP@UiT for 🥇 in Task B. 👏🎉 (4/4)



Urja Khurana Reposted

Yay! ✨ @CLTLVU PhDs @mtichiel , @urjakh , @Sel_Baez , @l__kra and me won the ArgMining 2022 shared task! Our fun short-term #NLProc summer side project! 😁 We combined inter-task-training on NLI, contrastive learning, & prompting: we'll ofcourse discuss it in our contribution.

Of course, before I forget, many congrats to CLTeamL🥇in Task A (runner-up🥈: AXiS@UniEd), and NLP@UiT for 🥇 in Task B. 👏🎉 (4/4)



Urja Khurana Reposted

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…


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

Tweet Image 1

Urja Khurana Reposted

This #CLTalk event with our invited speaker @norahollenstein is happening *tomorrow*! 🤩🥳 If you'd like to hear & speak to Nora, visiting us from Copenhagen, then join us tomorrow afternoon! ✨ (Drinks, snacks, and #NLProc: what more could you want?)

April 20 at 15.30 our lab will host the excellent dr. @norahollenstein for an invited talk "Leveraging Cognitive Signals in #NLProc", using cognitive (brain & eye-tracking) data. Then: drinks & snacks!🥂 Want to hear & meet Nora? Join us @ VU main building, room 11A24! ✨



Urja Khurana Reposted

April 20 at 15.30 our lab will host the excellent dr. @norahollenstein for an invited talk "Leveraging Cognitive Signals in #NLProc", using cognitive (brain & eye-tracking) data. Then: drinks & snacks!🥂 Want to hear & meet Nora? Join us @ VU main building, room 11A24! ✨


Urja Khurana Reposted

Today we were at the @networkinstvu 's event on interdisciplinarity in the Digital Society! ✨ CLTL's @urjakh presented work on careful definitions in hatespeech detection, @l__kra on explainability in human-robot interaction, & @myrthereuver on #NLProc for diversity in newsrec!


Loading...

Something went wrong.


Something went wrong.