Bringing Emerging Architectures to Sequence Labeling in NLP
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908895192023040 |
|---|---|
| author | Ezquerro, Ana Gómez-Rodríguez, Carlos Vilares, David |
| author_facet | Ezquerro, Ana Gómez-Rodríguez, Carlos Vilares, David |
| contents | Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bringing Emerging Architectures to Sequence Labeling in NLP Ezquerro, Ana Gómez-Rodríguez, Carlos Vilares, David Computation and Language Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks. |
| title | Bringing Emerging Architectures to Sequence Labeling in NLP |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.25918 |