LLMs can’t parse (yet) LLMs can’t parse (yet)

LLMs can't parse (yet) --- New Blog Post!

juriopitz.com/2025/08/26/l...

NLP RELIES on Linguistics: direct.mit.edu/coli/article...

OCR-Robust Embeddings: aclanthology.org/2025.finding...

Multi-Lingual Loanwords: aclanthology.org/2025.acl-lon...

Happy to share that my amazing co-authors will be presenting some of our recent work at ACL 2025 next week!

If you’re interested in these topics please feel free to drop by and connect.

(Paper links in comments 👇)

I might be able to hire a postdoc for this fall in computational linguistics at UT Austin. Topics in the general LLM + cognitive space (particularly reasoning, chain of thought, LLMs + code) and LLM + linguistic space. If this could be of interest, feel free to get in touch!

Applications are now open for the graduate programme in "Linguistic Computing" at Università Cattolica del Sacro Cuore! #Milan #NLProc #artificalintelligence
www.unicatt.it/en/programme...

Our survey highlights the enduring influence of linguistics on #NLProc. We emphasize 6 facets: Resources, Evaluation, Low-resource settings, Interpretability, Explanation, and the Study of language.

Happy to share that our paper, "Natural Language Processing RELIES on Linguistics," will appear in Computational Linguistics!

Preprint: arxiv.org/abs/2405.05966

Interpretable Text Embeddings and Text Similarity Explanation: A Primer Text embeddings and text embedding models are a backbone of many AI and NLP systems, particularly those involving search. However, interpretability challenges persist, especially in explaining obtaine...

Interpretable Text Embeddings and Text Similarity Explanation: A Primer

Provides a comprehensive overview of methods for explaining text embeddings and similarity scores, covering space shaping, set-based, and attribution approaches.

📝 arxiv.org/abs/2502.14862

Hello 🦋!

#nlproc #compling #machinelearning