@eusondavid

Assistant Professor at Universidade da Coruña

Joined May 2010
  • Tweets101
  • Following197
  • Followers261
3Media
We’ll also present “Sequence Labeling for Constituent Parsing: A Comparative Study and Encoding Innovations,” by Diego Roca, myself, and @carlosgr_nlp at #EMNLP2026 We compare parsing linearizations across many languages and introduce new variants aclanthology.org/2026.cl-2.3…

Sequence Labeling for Constituent Parsing: A Comparative Study and Encoding Innovations

Diego Roca, David Vilares, Carlos Gómez-Rodríguez. Computational Linguistics, Volume 52, Issue 2 - June 2026. 2026.

aclanthology.org
1
1
99
We’ll present “Synthetic Data Characterization via Training Dynamics” by Irene Lago, @anaezquerro_ and myself at Findings of #EMNLP2026. We study how TD can characterize and compare synthetic and human-written data across tasks, models, and scales. arxiv.org/pdf/2609.39447
2
4
200
Looking for emergency reviewers for ARR in the parsing area. Does anyone know someone who might be available (or be available themselves)? It would be hugely appreciated! 🙏
164
Congrats to Alberto Muñoz-Ortiz, who successfully defended his PhD thesis last Friday!! 🎉And thank you to the wonderful committee for making this day even more special: Miryam de Lhoneux (@mdlhx), Marcos Garcia (@m_garthia), and @miguel_a_alonso.
3
8
1,008
.@anaezquerro_ presenting our work on graph parsing as tagging at #EMNLP2025 !!!
2
5
699
Today, @anaezquerro_ 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-lo…
4
448
Happy to share that our paper 'Document-level event extraction from Italian crime news using minimal data' has been published: sciencedirect.com/science/ar… #nlp #nlproc
1
367
📓Baseline Notebooks: - Fine-tuning BERT-based models - NCRF++ models via GitHub 💡Check the repo! github.com/mmaguero/guarani-… 📖Check out the publication here: - digibug.ugr.es/handle/10481/… #NLP #AffectiveComputing #LowResourceLanguages #Guarani #Jopara #SentimentAnalysis #AIForAll

GitHub - mmaguero/guarani-multi-affective-analysis: Multidimensional Affective Analysis for...

Multidimensional Affective Analysis for Guarani/Jopara - mmaguero/guarani-multi-affective-analysis

github.com
1
1
2
467
Highlights: 🧵Corpora: - Emotion Recognition - Humor Detection - Offensive Language Identification 💻Base Models for Fine-Tuning (trained on Guarani Wiki): - From scratch: BERT-based tiny, small, base and large models - Continuously pre-trained models: m-BERT and BETO
1
1
2
231
🚀 Multidimensional Affective Analysis for Guarani/Jopara! 🌎 This project explored affective computing for low-resource languages, focusing on emotion recognition, humor detection, and offensive language identification in Guarani and Jopara (a code-switching mix with Spanish).
1
3
8
390
Today at 14:00, we'll be presenting "Dependency Graph Parsing as Sequence Labeling," by @anaezquerro_, @eusondavid, and @carlosgr_nlp at #EMNLP2024! Join us at the poster session in Riverfront Hall. 🔗 Paper: aclanthology.org/2024.emnlp-…
6
11
1,096
🌴 On our way to Miami for #EMNLP2024 to present two papers! 📄 - Revisiting Supertagging for Faster HPSG Parsing (@OlgaZamaraeva, @carlosgr_nlp) - Dependency Graph Parsing as Sequence Labeling (w/ @anaezquerro_, @eusondavid, @carlosgr_nlp)
3
8
706
📰Xa dispoñible no #RUC e #Zenodo o traballo do grupo GI-LYS e da @FIC_UDC: "From Partial to Strictly Incremental Constituent Parsing" aclanthology.org/2024.eacl-s… hdl.handle.net/2183/36570 zenodo.org/records/11365483
3
4
1,142
📰Xa dispoñible no #RUC e #Zenodo o traballo do grupo @lysresearch e da @FIC_UDC: "4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees" aclanthology.org/2023.emnlp-… hdl.handle.net/2183/36571 zenodo.org/records/11365726
3
3
973
Finding that many reviewers for #eacl2023, like myself often when reviewing, feel that "strengths/weaknesses" and "reason to accept/reasons to reject" are roughly equivalent. Any views on how these two are important and different?
1
3
To me, at least in theory, reasons to reject should be something stronger than weaknesses, but in practice, when it comes to reviewing, I see many choose to copy&paste from one field to the other, and many times both fields contain overlapping information.
Cheers mates, for a glorious Wednesday
108
15,011
839
88,161
If you're interested in making NLP/AI equally useful for all of us, and perhaps more responsible, here's a chance to join CoAStaL/UCPH [coastalcph.github.io/] as a PhD student: ddsa.dk/event2/ddsa-phd-fell…
4
5
Any volunteers out here willing to do an emergency review for EACL 2023 - Multidisciplinary and NLP Applications track?
2
Interested in working on biases in AI? There is an open PhD position in my new group on Diversity-Aware NLP Models at @Stuttgart_IRIS @Uni_Stuttgart. More info: ims.uni-stuttgart.de/institu… . Please RT.
12
2
11
Load more