📄 Read the full preprint on arXiv: arxiv.org/abs/2605.12515

Sincere thanks to my supervisors
Anna Korhonen & @iaugenstein.bsky.social 🤗

#NLP #LLMs #Interpretability #MultilingualNLP
@cambridgeltl.bsky.social @copenlu.bsky.social

Arrived in Singapore for #ICLR2025 and will be presenting PROVENCE on Friday, Poster session 3 at 10am, poster #255!

Blogpost: huggingface.co/blog/nadiinc...

Will be happy to meet & chat about #LLMs, #RAG, #InformationRetrieval and #MultilingualNLP :)

#NLProc @naverlabseurope

Both projects, including corpora, model weights, code, and evaluations, are fully open-source! 🔓 📄 MaLA Corpus: www.olaresearch.org/MaLA/ 📄 EMMA-500 Suite: www.olaresearch.org/EMMA-500-Gen2/
#NLProc #LLMs #MultilingualNLP #AI #MachineTranslation #OpenSource

Contextual lexical methods outperform raw LLM prompting for Hindi pregroup assignment (64.56% accuracy), while symbolic lexical repair improves LLM outputs. This advances scalable grammatical type annotation for multilingual quantum NLP pipelines.

#QuantumNLP #MultilingualNLP #Research

A streamlined pipeline selects compact typological features and imputes missing data, yielding vectors that boost multilingual NLP accuracy. Accepted for EMNLP 2025 on 24 Sep 2025. Read more: https://getnews.me/compact-language-typology-improves-multilingual-nlp/ #multilingualnlp #typology #language

The study proposes Tokenization Parity (TP) and Information Parity (IP) metrics, evaluating dialect classification, topic classification, and extractive QA across Latin and non‑Latin scripts. https://getnews.me/tokenization-biases-impact-multilingual-dialect-nlp/ #tokenizationparity #multilingualnlp

HiDAC, a dual‑adapter model, hits 67.5% accuracy on DISRPT 2025 discourse classification while using far fewer trainable parameters than full fine‑tuning. Read more: https://getnews.me/hierarchical-dual-adapter-boosts-multilingual-discourse-classification/ #dualadapter #multilingualnlp #disrpt2025

Come see the full results at #LREC2026, May 14, 5:20 PM - 7:00 PM (GMT+2), 344, Poster Area 1

🔗 arxiv.org/pdf/2511.01187

#LREC2026 #NLP #AIBias #LLMs #MultilingualNLP #ResponsibleAI

🎧 Full conversation:
🎬 YouTube: www.youtube.com/watch?v=L9Sp...
🎙️ Spotify: open.spotify.com/episode/2Kq7...
🍎 Apple Podcasts: podcasts.apple.com/ca/podcast/m...
📄 Paper: arxiv.org/abs/2406.03368
#WiAIR #WomenInAI #AIResearch #MultilingualNLP #Typology #LanguageDiversity

Don’t miss this #WiAIR episode with Dr. Annie Lee!
🎬 YouTube: www.youtube.com/watch?v=L9Sp...
🎙️ Spotify: open.spotify.com/episode/2Kq7...
🍎 Apple: podcasts.apple.com/ca/podcast/w...
#WomenInAI #KnowledgeBase #MultilingualNLP #AIResearch #Linguistics

This builds on the foundational harvesting work by Patrice Lopez & James Howison (SoftCite project), and is a collaboration with @DFKI, @HUBerlin, @CommonCrawl & Uni Mannheim.

Attending LREC? Let's connect!👋

#NLP #ScientificNLP #MultilingualNLP #SciLaD #ScienciaLAB #grobid
5/5