What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation

TL;DR

This paper introduces large, manually annotated datasets for acronym identification and disambiguation in the scientific domain, addressing limitations of previous datasets and demonstrating the superiority of a new deep learning model.

Contribution

The paper creates the first large-scale, manually annotated datasets for AI and AD in the scientific domain and proposes a novel deep learning model utilizing sentence syntax.

Findings

Existing models lag behind human performance on new datasets.

The proposed model outperforms state-of-the-art on the AD dataset.

New datasets enable better research and model development in acronym understanding.

Abstract

Acronyms are the short forms of phrases that facilitate conveying lengthy sentences in documents and serve as one of the mainstays of writing. Due to their importance, identifying acronyms and corresponding phrases (i.e., acronym identification (AI)) and finding the correct meaning of each acronym (i.e., acronym disambiguation (AD)) are crucial for text understanding. Despite the recent progress on this task, there are some limitations in the existing datasets which hinder further improvement. More specifically, limited size of manually annotated AI datasets or noises in the automatically created acronym identification datasets obstruct designing advanced high-performing acronym identification models. Moreover, the existing datasets are mostly limited to the medical domain and ignore other domains. In order to address these two limitations, we first create a manually annotated large AI dataset for scientific domain. This dataset contains 17,506 sentences which is substantially larger than previous scientific AI datasets. Next, we prepare an AD dataset for scientific domain with 62,441 samples which is significantly larger than the previous scientific AD dataset. Our experiments show that the existing state-of-the-art models fall far behind human-level performance on both datasets proposed by this work. In addition, we propose a new deep learning model that utilizes the syntactical structure of the sentence to expand an ambiguous acronym in a sentence. The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.