EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Skeleton-based approach for semantic textual similarity

Hao Wu, Degen Huang, Xiaohui Lin

Natural Language Processing · 2026-07 · 32 (4) · 430-450

DOI: 10.1017/nlp.2026.10025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Natural Language Processing, online erschienen am 09.06.2026. Verfasst von Hao Wu und 2 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic textual similarity (STS) is to measure semantic equivalence between sentences; it plays an important role in natural language processing (NLP) tasks. The major core of STS is text representation. This paper studies how to obtain a sentence skeleton for text representation in STS. Unlike most existing syntax models, we propose a skeleton-based reinforcement learning method to identify the skeleton and construct sentence representations. Parallel networks are adopted to extract features of different dimensions in the sentence. In the framework of parallel networks, two sentence representation models are designed: context constrained LSTM (CC-LSTM) and Adorned skeleton LSTM (AS-LSTM). CC-LSTM builds the sentence representation by constraining the word context. AS-LSTM constructs the sentence representation through using the identified skeleton and its qualifiers. Our approach achieves good results without using external resources. Especially AS-LSTM, which outperforms the state-of-the-art without using external resources in the SICK dataset.

Zitieren

APA

Wu, H., Huang, D., & Lin, X. (2026). Skeleton-based approach for semantic textual similarity. Natural Language Processing, 32(4), 430-450. https://doi.org/10.1017/nlp.2026.10025

Vancouver

Wu H, Huang D, Lin X. Skeleton-based approach for semantic textual similarity. Natural Language Processing. 2026;32(4):430-450. doi:10.1017/nlp.2026.10025

BibTeX
@article{Wu2026,
  author = {Wu, Hao and Huang, Degen and Lin, Xiaohui},
  title = {Skeleton-based approach for semantic textual similarity},
  journal = {Natural Language Processing},
  year = {2026},
  volume = {32},
  number = {4},
  pages = {430--450},
  doi = {10.1017/nlp.2026.10025}
}
Kostenlos starten →