Patrick Haller

How should computational (psycho)linguists properly apply token-level language models to the field’s inherently character-level problems? We try to bring some clarity in this new EMNLP paper 📣 Spoiler: you can (and should!) convert an LM over tokens into an LM over characters.

Excited for tomorrow to present our work on LLM response stability in the context of political bias assessment at @COLM_conf! Stop by between 9 and 11 at poster #39. Joint work w/@j_vamvas and @LenaAJaeger. 🔗 openreview.net/pdf?id=7xUtka9…

📖👀 We're excited to present PoTeC -- The Potsdam Textbook Corpus! PoTeC is a German naturalistic eye-tracking-while-reading corpus that can be used to study expert reading behavior. Check out the pre-print: arxiv.org/abs/2403.00506

Really excited about our new preprint: arxiv.org/abs/2402.04251 Generating high-quality machine translations can be accelerated by using reference aggregation – a new technique for MBR utility estimation that is in 𝒪(𝑛) instead of 𝒪(𝑛²). Work with @RicoSennrich at @cl_uzh

🔍Looking for some #multilingual #LLM reading for the holidays or just that last minute stocking filler? 🎅 👀Look no further! Our new #preprint explores what's needed to get your chat LLM speaking languages other than English! 📄arxiv.org/abs/2312.12683

📢 Interested in #eyemovements for #NLP? Or wanna chat about cognitive enhancement and interpretability of #LMs? 💃 Come by our poster on sythesizing human eye movements on Friday at 11! #EMNLP2023

how do you evaluate systems that generate non-standardized #dialects? check out our WMT23 paper 📜arxiv.org/abs/2311.16865 — with @chantalamrhein, @flschottmann, and @RicoSennrich

Check out the pre-print of our #EMNLP2023 paper on ScanDL, a diffusion model that generates human-like eye movements on texts. With @qube_si, @padraiglindrome, @theDebbister, Paul Prasse, and @LenaAJaeger. arxiv.org/abs/2310.15587