EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semantic enrichment of neural word embeddings: Leveraging taxonomic similarity for enhanced distributional semantics

Dongqiang Yang, Xinru Zhang, Tonghui Han, Yi Liu

Natural Language Processing · 2025-11 · 31 (6) · 1423-1449

DOI: 10.1017/nlp.2025.10005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Natural Language Processing, online erschienen am 30.07.2025. Verfasst von Dongqiang Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 108 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data-driven neural word embeddings (NWEs), grounded in distributional semantics, can capture various ranges of linguistic regularities, which can be further enriched by incorporating structured knowledge resources. This work proposes a novel post-processing approach for injecting semantic relationships into the vector space of both static and contextualized NWEs. Current solutions to retrofitting (RF) word embeddings often oversimplify the integration of semantic knowledge, neglecting the nuanced differences between relationships, which may result in suboptimal performance. Instead of applying multi-thresholding to distance boundaries in metric learning, we compute taxonomic similarity to dynamically adjust these boundaries during the semantic specialization of word embeddings. Benchmark evaluations on both static and contextualized word embeddings demonstrate that our dynamic-fitting (DF) approach produces SOTA correlation results of 0.78 and 0.76 on SimLex-999 and SimVerb-3500, respectively, highlighting the effectiveness of incorporating multiple semantic relationships in refining vector semantics. Our approach also outperforms existing RF methods in both supervised and unsupervised semantic relationships recognition tasks. It achieves top accuracy scores for hypernymy detection on the BLESS, WBLESS, and BIBLESS datasets (0.97, 0.89, and 0.83, respectively) and an F1 score of over 0.60 on four types of semantic relationship classification in the shared Subtask-2 of CogALex-V, surpassing all participant systems. In the analogy reasoning task of the Bigger Analogy Test Set, our approach outperforms existing RF methods on inferring relational similarity. These consistent improvements across various lexical semantics tasks suggest that our DF approach can effectively integrate distributional semantics with symbolic knowledge resources, thereby enhancing the representation capacity of word embeddings in downstream applications.

Zitieren

APA

Yang, D., Zhang, X., Han, T., & Liu, Y. (2025). Semantic enrichment of neural word embeddings: Leveraging taxonomic similarity for enhanced distributional semantics. Natural Language Processing, 31(6), 1423-1449. https://doi.org/10.1017/nlp.2025.10005

Vancouver

Yang D, Zhang X, Han T, Liu Y. Semantic enrichment of neural word embeddings: Leveraging taxonomic similarity for enhanced distributional semantics. Natural Language Processing. 2025;31(6):1423-1449. doi:10.1017/nlp.2025.10005

BibTeX
@article{Yang2025,
  author = {Yang, Dongqiang and Zhang, Xinru and Han, Tonghui and Liu, Yi},
  title = {Semantic enrichment of neural word embeddings: Leveraging taxonomic similarity for enhanced distributional semantics},
  journal = {Natural Language Processing},
  year = {2025},
  volume = {31},
  number = {6},
  pages = {1423--1449},
  doi = {10.1017/nlp.2025.10005}
}
Kostenlos starten →