Work

Better heads do not guarantee better binarized constituency parsing

Year: 2026

Type: preprint

Abstract: We revisit punctuation-aware tree binarization for constituency parsing and ask whether dependency-induced headedness improves binary parser supervision. Although learned heads substantially outperform rule-based heads in intrinsic head prediction, they do not yield consistent parsing gains after debinarization. In particular, punctuation-conditioned evaluation shows that learned headedness underperforms rule-based binarization in macro-average punctuation-sensitive $F_1$, despite a small overall gain on CTB. Similar instability appears under cross-treebank transfer. These results suggest that \ycc{linguistically grounded} headedness is not necessarily parser-optimal when used as a binarization control signal. The paper presents a negative result: better head prediction does not imply better punctuation-sensitive constituency parsing.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2605.28131

Authors: Qi, Zeyao, Chen, Yige, Klinger, Eitan, Wadhwa, Vivaan, Park, Jungyeul

Institutions: University of British Columbia, Chinese University of Hong Kong, Korea Advanced Institute of Science and Technology, Daejeon Institute of Science and Technology

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7162696587

Cites:

Cited by:

Related to: