Knowledge-Guided Paraphrase Identification
Knowledge-Guided Paraphrase Identification
复制标题
DOI：
10.18653/v1/2021.findings-emnlp.72
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Haoyu Wang;Fenglong Ma;Yaqing Wang;Jing Gao
中科院分区：
文献类型：
--
作者：
Haoyu Wang;Fenglong Ma;Yaqing Wang;Jing Gao
意译识别（释义识别）是自然语言处理中的一项基本任务，是识别两个句子是否表达相同或相似的意思，这是一个二元分类问题。近年来，类bert预训练语言模型已成为各种PI模型框架的热门选择，但几乎所有现有方法都考虑一般领域文本。当这些方法应用于特定领域时，现有模型由于缺乏专业知识而无法做出准确的预测。鉴于这一挑战，我们提出了一个新的框架，即Knowing，它可以利用外部非结构化的维基百科知识来准确地识别释义。我们建议通过BM25模型从维基百科中挖掘与给定句子相关的概念概要知识。在检索相关的大纲知识后，Knowing基于两个句子的语义信息和大纲知识进行预测。此外，我们还提出了一种基于语义信息的预测和基于知识的预测聚合的门控机制。在两个公共数据集上进行了广泛的实验：PARADE（计算机科学领域数据集）和clinicalSTS2019（生物医学领域数据集）。结果表明，所提出的know方法优于目前最先进的方法。
Paraphrase identification (PI), a fundamental task in natural language processing, is to identify whether two sentences express the same or similar meaning, which is a binary classification problem. Recently, BERT-like pretrained language models have been a popular choice for the frameworks of various PI models, but almost all existing methods consider general domain text. When these approaches are applied to a specific domain, existing models cannot make accurate predictions due to the lack of professional knowledge. In light of this challenge, we propose a novel framework, namely Knowing, which can leverage the external unstructured Wikipedia knowledge to accurately identify paraphrases. We propose to mine outline knowledge of concepts related to given sentences from Wikipedia via BM25 model. After retrieving related outline knowledge, Knowing makes predictions based on both the semantic information of two sentences and the outline knowledge. Besides, we propose a gating mechanism to aggregate the semantic information-based prediction and the knowledge-based prediction. Extensive experiments are conducted on two public datasets: PARADE (a computer science domain dataset) and clinicalSTS2019 (a biomedical domain dataset). The results show that the proposed Knowing outperforms state-ofthe-art methods.