Article ; Online: Better synonyms for enriching biomedical search.
Journal of the American Medical Informatics Association : JAMIA
2020 Volume 27, Issue 12, Page(s) 1894–1902
Abstract: Objective: In a biomedical literature search, the link between a query and a document is often not established, because they use different terms to refer to the same concept. Distributional word embeddings are frequently used for detecting related words ...
| Abstract | Objective: In a biomedical literature search, the link between a query and a document is often not established, because they use different terms to refer to the same concept. Distributional word embeddings are frequently used for detecting related words by computing the cosine similarity between them. However, previous research has not established either the best embedding methods for detecting synonyms among related word pairs or how effective such methods may be. Materials and methods: In this study, we first create the BioSearchSyn set, a manually annotated set of synonyms, to assess and compare 3 widely used word-embedding methods (word2vec, fastText, and GloVe) in their ability to detect synonyms among related pairs of words. We demonstrate the shortcomings of the cosine similarity score between word embeddings for this task: the same scores have very different meanings for the different methods. To address the problem, we propose utilizing pool adjacent violators (PAV), an isotonic regression algorithm, to transform a cosine similarity into a probability of 2 words being synonyms. Results: Experimental results using the BioSearchSyn set as a gold standard reveal which embedding methods have the best performance in identifying synonym pairs. The BioSearchSyn set also allows converting cosine similarity scores into probabilities, which provides a uniform interpretation of the synonymy score over different methods. Conclusions: We introduced the BioSearchSyn corpus of 1000 term pairs, which allowed us to identify the best embedding method for detecting synonymy for biomedical search. Using the proposed method, we created PubTermVariants2.0: a large, automatically extracted set of synonym pairs that have augmented PubMed searches since the spring of 2019. |
|---|---|
| MeSH term(s) | Algorithms ; Biomedical Research ; Information Storage and Retrieval/methods ; Linguistics ; Probability ; PubMed ; Terminology as Topic |
| Language | English |
| Publishing date | 2020-10-15 |
| Publishing country | England |
| Document type | Journal Article ; Research Support, N.I.H., Intramural |
| ZDB-ID | 1205156-1 |
| ISSN | 1527-974X ; 1067-5027 |
| ISSN (online) | 1527-974X |
| ISSN | 1067-5027 |
| DOI | 10.1093/jamia/ocaa151 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
More links
Kategorien
In stock of ZB MED Cologne/Königswinter
| Zs.A 4128: Show issues | Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (2.OG) ab Jg. 2022: Lesesaal (EG) |
|||
| Zs.MO 312: Show issues |
Order via subito
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.