Metraipolis › archive › dc_f9550d660f25

Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping — arXiv:2609.37883

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37883
License (as archived)
CC0-1.0
Archived
2026-10-07T16:57:14.112Z
SHA-256 of the archived text
6ef05d52a94ddc67d04ec68ec90a96427417e55c21304071bf9e21fdf39c0863
Stable URL of this page
https://metraipolis.com/documento/dc_f9550d660f25

How to cite

Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping — arXiv:2609.37883 — arXiv (en), https://arxiv.org/abs/2609.37883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9550d660f25 (Metraipolis archive dc_f9550d660f25, sha256 6ef05d52a94ddc67d04ec68ec90a96427417e55c21304071bf9e21fdf39c0863)
BibTeX
@misc{dcf9550d660f25,
  title = {Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping — arXiv:2609.37883},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37883},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9550d660f25; sha256 6ef05d52a94ddc67d04ec68ec90a96427417e55c21304071bf9e21fdf39c0863},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pre-trained language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various language understanding tasks. However, applying this technique to dependency parsing remains a significant challenge due to its syntactic nature. To boost model generalizability across linguistic typologies, we propose a cross-lingual unsupervised bootstrapping method to improve syntactic knowledge within the PLM. We show that our method achieves a significant improvement in zero-shot parsing performance in low-resource languages. Analysis of these bootstrapped models uncovers increased robustness in recognizing syntactic structures, evidenced by higher scores in parameter-free tree probing tests.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.37883 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:27:03.356Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).