David Vilares

. anaezquerro.bsky.social presenting our work on graph parsing as tagging at #EMNLP2025 !!!

🌱 I Simposio sobre IA Verde 🌱

📅 25 y 26 noviembre | 📍 CITIC, A Coruña

💻 Modalidad híbrida | Inscripción gratuita: forms.cloud.microsoft/r/KW0MrUES0L...

👉 Más info: catedrainditexalgoritmosverdes.com/es/simposio-...

Hierarchical Bracketing Encodings for Dependency Parsing as Tagging Ana Ezquerro, David Vilares, Anssi Yli-Jyrä, Carlos Gómez-Rodríguez. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Today, @anaezquerro.bsky.social will be presenting our paper 'Hierarchical Bracketing Encodings for Dependency Parsing as Tagging' at #ACL2025NLP 🇦🇹

Room 1.86 (Session from 14:00 to 15:30).

Paper: aclanthology.org/2025.acl-lon...

Document-level event extraction from Italian crime news using minimal data Event extraction from unstructured text is a critical task in natural language processing, often requiring substantial annotated data. This study pres…

Happy to share that our paper 'Document-level event extraction from Italian crime news using minimal data' has been published: www.sciencedirect.com/science/arti... #nlp #nlproc

Justamente, la historia de muchos gallegos. Mucho mérito aprender así el idioma y no sabía que se podía ver la TVG desde allí. Si algún día visitas Caión estaría general poder aprovechar y organizar una charla invitada.

Siendo yo de Vigo, tengo curiosidad por saber lo del Celta 🩵

Could you add me, too? aclanthology.org/people/d/dav... Thanks!

All the ACL chapters are here now: @aaclmeeting.bsky.social @emnlpmeeting.bsky.social @eaclmeeting.bsky.social @naaclmeeting.bsky.social #NLProc

Hello, Computational linguistics/NLP world in Bluesky! We're creating the same accounts on other social media platforms in Bluesky! #NLProc

Today at 14:00, @anaezquerro.bsky.social and @carlosg.bsky.social will be presenting our paper "Dependency Graph Parsing as Sequence Labeling" at #EMNLP2024! Join them at the poster session in Riverfront Hall.

Paper: aclanthology.org/2024.emnlp-m...

Our paper, "Dependency Graph Parsing as Sequence Labeling" (with anaezquerro.bsky.social, myself, and @carlosg.bsky.social), will be presented this Tuesday at #EMNLP2024 in Miami!

The paper is already in the ACL Anthology: aclanthology.org/2024.emnlp-m...

Our paper "From Partial to Strictly Incremental Constituent Parsing" (w/ Ana Ezquerro and @carlosg.bsky.social) is now available on arXiV and it will be presented at #EACL2024. We explore the capacities of various incremental encoders and decoders for this classical task: arxiv.org/abs/2402.02782

4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees We introduce an encoding for parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word. The bits in each word's label represent (1)...

We just submitted to arXiv our paper (w/ @carlosg.bsky.social and Diego Roca): "4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees", which we will be presenting at #EMNLP2023, in Singapore!

arxiv.org/abs/2310.14319

Lexical Processing Strongly Affects Reading Times But Not Skipping During Natural Reading Abstract. In a typical text, readers look much longer at some words than at others, even skipping many altogether. Historically, researchers explained this variation via low-level visual or oculomotor...

New paper, out in Open Mind

We find that in reading, the brain uses 2 strategies to control the eyes

Reading times (fixation durations) depend on linguistic processing, but skipping (fix. location) mostly depends on low-level oculomotor processing

#CogSci 🧠🤖 🧠📈

direct.mit.edu/opmi/article...

Happy to have this paper accepted at IJCNLP-AACL 2023: "On the Challenges of Fully Incremental Neural Dependency Parsing", led by Ana Ezquerro. The preprint is now available here: arxiv.org/abs/2309.16254

Happy to have this paper accepted at IJCNLP-AACL 2023, led by Alberto Muñoz-Ortiz: Assessment of Pre-Trained Models Across Languages and Grammars arxiv.org/abs/2309.11165

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions,... Most interpretability research in NLP focuses on understanding the behavior and features of a fully trained model. However, certain insights into model behavior may only be accessible by observing...

Have you ever written a paper and looked at it and realized it should have been three papers and possibly even more? I felt that with our latest work about phase transitions in masked language model training, led by Angie Chen. We found so many cool things that deserve so much followup work!

Found this interesting QA on human language and its evolution: bmcbiol.biomedcentral.com/articles/10....

Hello, Bluesky!