Oli Danyi Liu

[CoNLL 2026 @conll_conf]

As a result, 12% of the papers in the review pool were desk rejected. Pulling this off in a timely manner was not easy, and was only possible thanks to our wonderful and dedicated reviewers and ACs!

[Yevgen Matusevych @Yevgen_M]

Interested in a paid PhD position in the Netherlands? Join me, Annemarie van Dooren, and @AriannaBisazza on a project to develop computational models of modal verb acquisition. A job ad will be out soon, but here's a preview: https://t.co/JNdnkyXDrW

[Andreas Grivas @andreasgrv]

📕⬇️ My thesis on 🚫unargmaxable outputs is online! Check it out if you want to learn more about how output layers constrain what neural networks can and cannot predict 👉 https://t.co/qr6NrsEHxy

[UKRI CDT in Natural Language Processing @Edin_CDT_NLP]

🏆🥳🙌Congratulations to (l-r) Dr Burchell @very_laurie, Dr Cardenas and Dr Moghe @nikita_moghe on their recent graduation from the UKRI CDT in NLP @InfAtEd ! All the very best in your respective careers! 🌠 🏆

[Christopher Potts @ChrisGPotts]

The Linear Representation Hypothesis is now widely adopted despite its highly restrictive nature. Here, @robert_csordas, Atticus Geiger, @chrmanning & I present a counterexample to the LRH and argue for more expressive theories of interpretability: https://t.co/wMQsuMum7O

[antonio vergari ⚔️ @tetraduzione]

Congrats to Dr. @andreasgrv who just defended his #PhD thesis on unargmaxability and constraints in deep learning, examined by Vlad Niculae and @driainmurray 🎉

A pity you could not (yet) see Andreas' beautifully designed thesis!

In the meantime, some pics from the pre-viva 👇

[Oli Danyi Liu @uililo1]

@Amrkeleg @Walid_Magdy @Edin_CDT_NLP Congratulations Amr! 🎉🎉

[Marianne de Heer Kloots (🦋/mdhk.net) @mariannedhk]

✨ Do current neural speech models show human-like linguistic biases in speech perception?

We took inspiration from classic phonetic categorization experiments to explore whether & where sensitivity to phonotactic context emerges in Wav2Vec2 models 🔍

📑 https://t.co/66XPdRPKcV

[Oli Danyi Liu @uililo1]

@ie2rfLin @cogsci_soc @Edin_CDT_NLP Thank you!

[Oli Danyi Liu @uililo1]

Happy to share that our paper won the @cogsci_soc computational modeling award for perception and action! #CogSci2024 @Edin_CDT_NLP

[Oli Danyi Liu @uililo1]

Paper with @larryniven4, Naomi Feldman, and Sharon Goldwater to appear in CogSci 2024: "A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech" https://t.co/Nz4y1Rhrsh (1/7)

[Oli Danyi Liu @uililo1]

@EhsanShareghi @cogsci_soc @Edin_CDT_NLP Thanks Ehsan :)

[Oli Danyi Liu @uililo1]

@Wenhao_NLP @cogsci_soc @Edin_CDT_NLP Thanks Wenhao!

[Oli Danyi Liu @uililo1]

@badr_nlp @cogsci_soc @Edin_CDT_NLP Thanks Badr!

[Oli Danyi Liu @uililo1]

I'll be presenting this paper as a poster at the HILS conference (July 9th) and as a talk at CogSci! (7/7)

[Oli Danyi Liu @uililo1]

Paper with @larryniven4, Naomi Feldman, and Sharon Goldwater to appear in CogSci 2024: "A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech" https://t.co/Nz4y1Rhrsh (1/7)

[Oli Danyi Liu @uililo1]

However, we found evidence that the effectiveness of these generalizations depends on the specific contexts, which suggests that this analysis alone may be insufficient to support the presence of context-invariant encoding. (6/7)