Punctuation-aware treebank tree binarization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909840861822976 |
|---|---|
| author | Klinger, Eitan Wadhwa, Vivaan Park, Jungyeul |
| author_facet | Klinger, Eitan Wadhwa, Vivaan Park, Jungyeul |
| contents | This article presents a curated resource and evaluation suite for punctuation-aware treebank binarization. Standard binarization pipelines drop punctuation before head selection, which alters constituent shape and harms head-child identification. We release (1) a reproducible pipeline that preserves punctuation as sibling nodes prior to binarization, (2) derived artifacts and metadata (intermediate @X markers, reversibility signatures, alignment indices), and (3) an accompanying evaluation suite covering head-child prediction, round-trip reversibility, and structural compatibility with derivational resources (CCGbank). On the Penn Treebank, punctuation-aware preprocessing improves head prediction accuracy from 73.66\% (Collins rules) and 86.66\% (MLP) to 91.85\% with the same classifier, and achieves competitive alignment against CCGbank derivations. All code, configuration files, and documentation are released to enable replication and extension to other corpora. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Punctuation-aware treebank tree binarization Klinger, Eitan Wadhwa, Vivaan Park, Jungyeul Computation and Language This article presents a curated resource and evaluation suite for punctuation-aware treebank binarization. Standard binarization pipelines drop punctuation before head selection, which alters constituent shape and harms head-child identification. We release (1) a reproducible pipeline that preserves punctuation as sibling nodes prior to binarization, (2) derived artifacts and metadata (intermediate @X markers, reversibility signatures, alignment indices), and (3) an accompanying evaluation suite covering head-child prediction, round-trip reversibility, and structural compatibility with derivational resources (CCGbank). On the Penn Treebank, punctuation-aware preprocessing improves head prediction accuracy from 73.66\% (Collins rules) and 86.66\% (MLP) to 91.85\% with the same classifier, and achieves competitive alignment against CCGbank derivations. All code, configuration files, and documentation are released to enable replication and extension to other corpora. |
| title | Punctuation-aware treebank tree binarization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.10951 |