
NLPnorth
@NLPnorth
Followers
976
Following
71
Media
45
Statuses
189
#NLProc research group @itukbh (IT University of Copenhagen, Denmark).
Copenhagen
Joined July 2020
๐The AI Gap: How Socioeconomic Status Affects Language Technology Interactions .๐ฅ @EliBassignana * @CurriedAmanda * Dirk Hovy.๐ ๐ฏWe call for inclusive NLP technologies to accommodate different SES and mitigate the digital divide.
0
0
2
๐ DECAF: A Dynamically Extensible Corpus Analysis Framework .๐ฅ @mxmeij @robvanderg @annargrs .๐ ๐ฏ DECAF supports generalization research with clear train/test separation at scale.
1
0
0
๐Identifying Open Challenges in Language Identification .๐ฅ @robvanderg .๐ฏย We identify and quantify a variety of challenges for language classification and identify cross-domain evaluation as a main bottleneck, where n-gram based models outperform transformer-based LMs.
2
0
0
๐ฃ Next week we will be in Vienna for @aclmeeting to present a couple of works from our lab! . Find more about each of them below ๐งต๐ . #NLP #NLProc #ACL2025NLP
1
1
5
Recently, @robvanderg and @mjjzha (AAU) participated in the TalentCLEF shared task on job title and skill matching. They show that prompting performs well for job titles, but encoder models still prevail for skill matching!. ๐ . #NLProc #NLP.
0
0
1
๐ข New #ACL2025 preprint by our postdoc @EliBassignana about the impact of socioeconomic status (SES) on the adoption and usage of language technologies!. A first step for better understanding the AI Gap across SES and develop more inclusive language technologies โ๏ธ๐ค. #NLProc.
The first paper of my postdoc is accepted at #ACL2025 Main ๐. "The AI Gap: How Socioeconomic Status Affects Language Technology Interactions". I'm very happy for my new collab with @MilaNLProc and super grateful to @VILLUMFONDEN for making it possible!. #NLProc #ACL2025NLP.
0
0
0
๐ Efficient Elicitation of Fictitious Nursing Notes from Volunteer Healthcare Professionals.๐ฅ Jesper, @ch_hardmeier.๐ฏ We introduce a data collection method and Danish dataset of fictitious nursing notes by prompting volunteers with situations.๐ March 3rd, 14.10 (Poster).
0
0
1
๐ DAKULTUR: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers.๐ฅ @mxmeij @mjjzha @EliBassignana Peter Trolle @robvanderg .๐ฏ A user study for analyzing the cultural awareness of LLMs in Danish.๐ March 2nd, 10:30 (NB-REAL).
1
0
1
๐ MORSED: Morphological Segmentation of Danish and its Effect on Language Modeling.๐ฅ @robvanderg Anette, Emil, Mikkel, Nicolaj, @mjjzha @EliBassignana .๐ฏ We create morphological segmenters for Danish and using them for LM training.๐ March 3rd, 14.10 (Poster session).
1
0
0
๐SnakModel: Lessons Learned from Training an Open Danish Large Language Model.๐ฅ @mjjzha @mxmeij @EliBassignana @robvanderg.๐๐ฏSnakmodel is an LLM continuously pre-trained on 13.6B Danish tokens and 3.7M instruction pairs.๐March 3rd, 10.45 (Ida-Euroopa).
1
0
0
Congratulations to Dr. @mizmarija for defending her thesis "Phonetic Vowel Representation for Cross-Lingual Automatic Speech Recognition"! Well deserved ๐๐
0
0
8
RT @EliBassignana: I'm in Bangkok for #ACL2024NLP ๐น๐ญ Looking forward to present our work "Dissecting Biases in Relation Extraction: A Crossโฆ.
0
7
0
Congratulations to our Dr. @EliBassignana for defending her thesis โCross-domain relation extractionโ! Very well-deserved and looking forward to your next steps! ๐ฅณ
6
3
45
RT @EliBassignana: I'm in Mexico City for #NAACL2024 ๐ฒ๐ฝ I'll present a poster at @_starsem on Friday morning where we introduce a tool forโฆ.
0
6
0