Metraipolis › archive › dc_98eb9551bb7b
Representing and Parsing Korean Constituency Structure at Different Levels of Granularity — arXiv:2608.27035
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27035
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T15:20:11.783Z
- SHA-256 of the archived text
93961486a2e4861c95795e9623a29a25ee364cbea35ab45bc1e8e2bc77f134fd- Stable URL of this page
https://metraipolis.com/documento/dc_98eb9551bb7b
How to cite
Representing and Parsing Korean Constituency Structure at Different Levels of Granularity — arXiv:2608.27035 — arXiv (en), https://arxiv.org/abs/2608.27035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98eb9551bb7b (Metraipolis archive dc_98eb9551bb7b, sha256 93961486a2e4861c95795e9623a29a25ee364cbea35ab45bc1e8e2bc77f134fd)
BibTeX
@misc{dc98eb9551bb7b,
title = {Representing and Parsing Korean Constituency Structure at Different Levels of Granularity — arXiv:2608.27035},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27035},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98eb9551bb7b; sha256 93961486a2e4861c95795e9623a29a25ee364cbea35ab45bc1e8e2bc77f134fd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Korean constituency parsing raises a representational challenge because the terminal units of a phrase-structure tree do not straightforwardly correspond to simple surface words. Korean eojeols are morphologically complex spacing units, and existing constituency resources differ in how they represent eojeol-internal morphology and non-overt elements. This paper compares three constituency parsing representations derived from the Penn Korean Treebank: Morpheme+XPOS, Eojeol+XPOS, and Eojeol+UPOS. We construct these representations by removing null elements, aligning Penn Korean phrase structure with overt eojeol tokens, preserving Penn Korean phrase labels where possible, and varying the terminal and preterminal layers. We then evaluate canonical non-binary transition-based constituency parsers in top-down, in-order, and bottom-up orders under a shared modeling and evaluation setup. All experiments use gold terminal segmentation and gold preterminal labels and therefore evaluate constituency parsing conditioned on gold morphosyntactic annotation. Eojeol terminals yield shorter transition sequences, but Eojeol+UPOS parsing substantially underperforms the morphologically richer conditions. Eojeol+XPOS narrows this gap, while Morpheme+XPOS gives the strongest results even after its predictions are projected to the eojeol terminal domain. Under these gold-annotation conditions, the results show that fine-grained morphological and XPOS representations provide valuable evidence for the evaluated parsers. This empirical finding concerns the information available for parsing and does not by itself determine the linguistically preferable terminal domain. Independently, linguistic and resource-design considerations motivate eojeol as a stable and interpretable surface domain for phrase-structure annotation, with morpheme-level and XPOS information retained as aligned morphosyntactic evidence. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.27035 — 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 2026-10-17T15:15:18.082Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).