Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputation

Jason Hoelscher-Obermaier, Edward Stevinson, Valentin Stauber, Ivaylo Zhelev, Viktor Botev, Ronin Wu, Jeremy Minton


Abstract
The most interesting words in scientific texts will often be novel or rare. This presents a challenge for scientific word embedding models to determine quality embedding vectors for useful terms that are infrequent or newly emerging. We demonstrate how Latent Semantic Imputation (LSI) can address this problem by imputing embeddings for domain-specific words from up-to-date knowledge graphs while otherwise preserving the original word embedding model. We use the MeSH knowledge graph to impute embedding vectors for biomedical terminology without retraining and evaluate the resulting embedding model on a domain-specific word-pair similarity task. We show that LSI can produce reliable embedding vectors for rare and out-of-vocabulary terms in the biomedical domain.
Anthology ID:
2022.wiesp-1.6
Volume:
Proceedings of the first Workshop on Information Extraction from Scientific Publications
Month:
November
Year:
2022
Address:
Online
Venue:
WIESP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
43–53
Language:
URL:
https://aclanthology.org/2022.wiesp-1.6
DOI:
Bibkey:
Cite (ACL):
Jason Hoelscher-Obermaier, Edward Stevinson, Valentin Stauber, Ivaylo Zhelev, Viktor Botev, Ronin Wu, and Jeremy Minton. 2022. Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputation. In Proceedings of the first Workshop on Information Extraction from Scientific Publications, pages 43–53, Online. Association for Computational Linguistics.
Cite (Informal):
Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputation (Hoelscher-Obermaier et al., WIESP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.wiesp-1.6.pdf