Church, Kenneth and Liu, Boxiang (2021) Acronyms and Opportunities for Improving Deep Nets. Frontiers in Artificial Intelligence, 4. ISSN 2624-8212
![[thumbnail of pubmed-zip/versions/4/package-entries/frai-04-732381-r3/frai-04-732381.pdf]](http://publish7promo.com/style/images/fileicons/text.png)
pubmed-zip/versions/4/package-entries/frai-04-732381-r3/frai-04-732381.pdf - Published Version
Download (1MB)
Abstract
Recently, several studies have reported promising results with BERT-like methods on acronym tasks. In this study, we find an older rule-based program, Ab3P, not only performs better, but error analysis suggests why. There is a well-known spelling convention in acronyms where each letter in the short form (SF) refers to “salient” letters in the long form (LF). The error analysis uses decision trees and logistic regression to show that there is an opportunity for many pre-trained models (BERT, T5, BioBert, BART, ERNIE) to take advantage of this spelling convention.
Item Type: | Article |
---|---|
Subjects: | Euro Archives > Multidisciplinary |
Depositing User: | Managing Editor |
Date Deposited: | 02 Mar 2023 05:24 |
Last Modified: | 06 Jul 2024 06:18 |
URI: | http://publish7promo.com/id/eprint/893 |