🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We present ‘Graph Neural Networks for Multiparallel Word Alignment’. Our method significantly improves word alignment quality, especially for low-resource languages.: ✏️Ayyoob Imani Lütfi Kerem Şenel Masoud Jalili François Yvon hinrich schuetze 📎arxiv.org/abs/2203.08654 🗣️25th PS6 10:45 am

🎉Happy to share that our paper “Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging” was accepted to #EMNLP2022 ! Joint work with Ayyoob Imani, Masoud Jalili, François Yvon, and hinrich schuetze. Preprint coming soon🍿! #NLProc

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages repo: github.com/cisnlp/Glot500 abs: arxiv.org/abs/2305.12182 HuggingFace: huggingface.co/cis-lmu/glot50…

An idea paper comes into play, offering an innovative solution: equipping LLMs with read-write memory. “RET-LLM: Towards a General Read-Write Memory for Large Language Models” 🔗:arxiv.org/abs/2305.14322 A joint work with Ayyoob Imani , Mohsen Fayyaz & hinrich schuetze (🧵2/4)

Excited that our paper "Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages" won the Area Chair Award at #ACL2023. Big kudos to our squad at CIS, LMU Munich who made it all happen. Peiqin Lin to present the findings. #NLProc

GlotLID: Language Identification for Low-Resource Languages abs: arxiv.org/abs/2310.16248 demo: huggingface.co/spaces/cis-lmu… repo: github.com/cisnlp/GlotLID

📣New paper 📣 We introduce MemLLM, a method to enhance language models by adding a read-write memory. By designing an interaction schema and constructing training data, we fine-tune a model to store and use facts with an external structured memory. 🧵