Better than BERT but Worse than Baseline
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 12 May 2021.
Builds on
12 of 33 references.
References · 12
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
- 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 320
- 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
- 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
- 2019Do NLP Models Know Numbers? Probing Numeracy in Embeddingscited by 159
- 2019Coreference Resolution as Query-based Span Predictioncited by 91
- 2020What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguationcited by 26
- 2020Biomedical named entity recognition using BERT in the machine reading comprehension frameworkcited by 22
- 2021Read, Retrospect, Select: An MRC Framework to Short Text Entity Linkingcited by 14
- 2020Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extractioncited by 11
Built on by
Not cited yet.