由 GPT 赋能的加速材料语言处理
Accelerated materials language processing enabled by GPT
AI总结：
本文提出用提示工程替代复杂架构的 GPT 赋能 MLP 流程，在小样本文档分类、NER 和抽取式 QA 上取得可比或更优性能，并展现自动纠正标注潜力。
摘要：
材料语言处理（MLP）是材料科学研究的关键推动因素之一，因为它能够从海量材料科学文献中提取结构化信息。以往研究提出了用于文本分类、命名实体识别（NER）和抽取式问答（QA）的高性能 MLP 模型，但这些模型需要复杂的模型架构、详尽的微调以及大量人工标注数据集。在本研究中，我们开发了由生成式预训练 Transformer（GPT）赋能的流程，其中以往 MLP 模型的复杂架构被提示工程的策略性设计所取代。首先，我们开发了一种 GPT 赋能的文档分类方法，用于筛选相关文档；仅使用小型数据集，该方法便取得了与以往模型相当的准确性和可靠性。其次，针对 NER 任务，我们设计了以实体为中心的提示，对这些提示进行少样本学习后，提升了三个开放数据集中大多数实体的性能。最后，我们开发了一个 GPT 赋能的抽取式 QA 模型，该模型提供了更好的性能，并展现了自动纠正标注的可能性。尽管我们的发现证实了 GPT 赋能 MLP 模型的潜力及其在可靠性和实用性方面的价值，但我们的科学方法和系统化路径适用于任何材料科学领域，以加速科学文献的信息提取。
英文摘要：
Materials language processing (MLP) is one of the key facilitators of materials science research, as it enables the extraction of structured information from massive materials science literature. Prior works suggested high-performance MLP models for text classification, named entity recognition (NER), and extractive question answering (QA), which require complex model architecture, exhaustive fine-tuning and a large number of human-labelled datasets. In this study, we develop generative pretrained transformer (GPT)-enabled pipelines where the complex architectures of prior MLP models are replaced with strategic designs of prompt engineering. First, we develop a GPT-enabled document classification method for screening relevant documents, achieving comparable accuracy and reliability compared to prior models, with only small dataset. Secondly, for NER task, we design an entity-centric prompts, and learning few-shot of them improved the performance on most of entities in three open datasets. Finally, we develop an GPT-enabled extractive QA model, which provides improved performance and shows the possibility of automatically correcting annotations. While our findings confirm the potential of GPT-enabled MLP models as well as their value in terms of reliability and practicability, our scientific methods and systematic approach are applicable to any materials science domain to accelerate the information extraction of scientific literature.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
