Better than BERT but Worse than Baseline

Autor:	Liu, Boxiang, Huang, Jiaji, Cai, Xingyu, Church, Kenneth
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	This paper compares BERT-SQuAD and Ab3P on the Abbreviation Definition Identification (ADI) task. ADI inputs a text and outputs short forms (abbreviations/acronyms) and long forms (expansions). BERT with reranking improves over BERT without reranking but fails to reach the Ab3P rule-based baseline. What is BERT missing? Reranking introduces two new features: charmatch and freq. The first feature identifies opportunities to take advantage of character constraints in acronyms and the second feature identifies opportunities to take advantage of frequency constraints across documents. Comment: 6 pages, 2 figures, 5 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2105.05915 Zobrazit plný text záznamu View this record from Arxiv