Lena S. Bolliger

PhD candidate in NLP @cl_uzh, University of Zurich.

[Gerasimos Lampouras @glampouras_NLP]

We are exhibiting at #ACL2025 in Vienna from July 28th to 30th!! Come visit us at booth 14 and have a chat with many of our experts (and me!), especially if interested in our hiring opportunities!!

https://t.co/fcbq95Pwn1

[Lena S. Bolliger @lsbolliger]

🤖 Interested in the cognitive alignment of LMs with humans? If you're at #EMNLP2024 🌴, come talk to me at 11:00 in Riverfront Hall, where I'll be presenting our work with @padraiglindrome and @LenaAJaeger .

📜 https://t.co/7ESW0s6KAr

[Tannon Kew @tannonk]

If you're at #EMNLP2024 in Miami 🌴 and interested in turning English-centric LLMs into polyglots, come talk to me at 14:00 in Poster Session B (Riverfront Hall), where I'll be presenting our work with @RicoSennrich and @flschottmann from @textshuttle!

📄 https://t.co/CnQ6suprog

[Lena S. Bolliger @lsbolliger]

🤖 We further release the LLMs' transition scores, attention scores, and hidden states of the stimulus generation process.

[Lena S. Bolliger @lsbolliger]

📢 Excited to share the release of EMTeC, the Eye Movements on Machine-Generated Texts Corpus!

w/ @padraiglindrome, I. Cretton, @qube_si, @tannonk, and @LenaAJaeger

Preprint: https://t.co/U2td5MlYTD
Data: https://t.co/2KUdRYdJFF

[Lena S. Bolliger @lsbolliger]

👁️ We release the raw eye-tracking data, the fixation sequence data, and the reading measure data. We also release a manually corrected version of the fixation data accounting for vertical drift. 📈

[Patrick Haller @padraiglindrome]

👀📖 Excited to share our #ACL2024 findings paper on how language models emulate readers with specific cognitive capacities. See 🧵

We'll present this work next week in Bangkok during the findings poster session 4 and at CMCL.

w/@lsbolliger and @LenaAJaeger

[Tannon Kew @tannonk]

🔍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!

📄https://t.co/l2HxgXh7vU

[Lena S. Bolliger @lsbolliger]

@verena_rieser Sure! Here you go: https://t.co/cJWZEYXl9u

[Lena S. Bolliger @lsbolliger]

📢 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

[Noëmi Aepli @noeminaepli]

how do you evaluate systems that generate non-standardized #dialects?
check out our WMT23 paper 📜https://t.co/y6ZKhRlBsg — with @chantalamrhein, @flschottmann, and @RicoSennrich

[Jannis Vamvas @j_vamvas]

Minimum Bayes Risk decoding has recently gained momentum in #NLProc.
However, a generic implementation for @huggingface Transformers was missing. Check out our new 𝗺𝗯𝗿 🔥repo, which is designed to work with any model and metric on the Hub: https://t.co/G5QIG0cZFm

[Lena S. Bolliger @lsbolliger]

@LenaAJaeger @UZH_ch @cl_uzh @weGotlieb @CuiDing_CL

[Lena S. Bolliger @lsbolliger]

Thus ScanDL could not only solve the problem of scarcity and unavailability of eye movement data in NLP settings, but it could also be used to pilot psycholinguistic experiments and generate data for statistical power simulations.

[Lena S. Bolliger @lsbolliger]

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.
https://t.co/cJWZEYWNjW

[Lena S. Bolliger @lsbolliger]

Importantly, a psycholinguistic analysis shows that ScanDL also emulates psycholinguistic key phenomena of human reading behavior, even more than cognitive models fitted on the same data.

[Lena Jäger @LenaAJaeger]

Happy to announce that we have two papers accepted at #EMNLP2023 main conference: 1) a diffusion model for generating synthetic eye movements in reading 2) using synthetic human-like eye movements to enhance NLU. Congratulations to @lsbolliger, @qube_si, @padraiglindrome, et al.!

[Zurich Computational Linguistics Group @cl_uzh]

Our group is hiring a researcher in language technology. The position is full-time and permanent!

The position is open until filled, but apply in the next few weeks for best chances!

https://t.co/0sGHL4jr2C