Better than BERT but Worse than Baseline
This work addresses abbreviation identification for natural language processing applications, but it is incremental as it builds on existing methods without achieving new state-of-the-art results.
The paper tackled the Abbreviation Definition Identification (ADI) task by comparing BERT-SQuAD with reranking features against the Ab3P rule-based baseline, finding that BERT with reranking improved over BERT without it but still underperformed the baseline.
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.