Acronyms and Opportunities for Improving Deep Nets

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...

Full description

Saved in:
Bibliographic Details
Published inFrontiers in artificial intelligence Vol. 4; p. 732381
Main Authors Church, Kenneth, Liu, Boxiang
Format Journal Article
LanguageEnglish
Published Switzerland Frontiers Media S.A 13.12.2021
Subjects
Ab3P
acronyms
Artificial Intelligence
BERT
deep nets
ERNIE
multiword expressions
multiword expressions
Ab3P
BERT
acronyms
deep nets
ERNIE
Online AccessGet full text
ISSN2624-8212
2624-8212
DOI10.3389/frai.2021.732381

Cover

More Information
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Edited by: Robert Krovetz, Lexical Research, United States
Michael Flor, Educational Testing Service, United States
Reviewed by: Luis Espinosa-Anke, Cardiff University, United Kingdom
This article was submitted to Language and Computation, a section of the journal Frontiers in Artificial Intelligence
ISSN:2624-8212
2624-8212
DOI:10.3389/frai.2021.732381