With so many articles of varying qualities being produced every moment, it is a very urgent task to screen outstanding articles and commit them to social media. To our best knowledge, there is a lack of datasets and mature research works in identifying high-quality articles. Consequently, we conduct some surveys and finalize 7 objective indicators to annotate the quality of 10k articles. During annotation, we find that many characteristics of high-quality articles (e.g., background) rely more on extensive external knowledge than inner semantic information of articles. In response, we link extracted article entities to Baidu Encyclopedia, then propose Knowledge Enhanced article Quality Identification (KE-QI) dataset. To make better use of external knowledge, we propose a compound model which fuses the text and external knowledge information via a gate unit to classify the quality of an article. Our experimental results on KE-QI show that with initialization of our pre-trained Node2Vec model, our model achieves about 78\% $F_1$, outperforming other baselines.
CASIMIR: A Corpus of Scientific Articles enhanced with Multiple Author-Integrated Revisions
Nantes Université(南特大学);École Centrale Nantes(南特中央理工学院);CNRS(法国国家科学研究中心);LS2N(南特数字科学实验室);Japanese French Laboratory for Informatics(日法信息学实验室);NII(日本国立信息学研究所)
University of Ljubljana, Faculty of Computer and Information Science(卢布尔雅那大学计算机与信息科学学院);Jožef Stefan Institute, Department of Knowledge Technologies(乔塞夫·斯塔芬研究所知识技术部门);Jožef Stefan International Postgraduate School(乔塞夫·斯塔芬国际研究生学院)
Improving Tagging Consistency and Entity Coverage for Chemical Identification in Full-text Articles
Korea University(高丽大学);University of California, San Diego(加州大学圣迭戈分校)
本文是关于我们的系统提交给BioCreative VII Track 2挑战的化学鉴别任务的技术报告。这一挑战的主要特点是数据由全文文章组成,而当前的数据集通常只包括标题和摘要。为了有效地解决这个问题,我们的目标是提高标签的一致性和实体覆盖率,使用各种方法,如在相同的文章中的多数表决命名实体识别(NER)和一个混合的方法,结合字典和神经模型进行规范化。在NLM-Chem数据集上的实验中,我们表明我们的方法提高了模型的性能,特别是在召回方面。最后,在挑战赛的官方评估中,我们的系统在NER中排名第一,表现明显优于基线模型和来自16个团队的80多个提交。
Enhancing Identification of Structure Function of Academic Articles Using Contextual Information
School of Information Management, Nanjing University(南京大学信息管理学院);Department of Information Management, Nanjing University of Science and Technology(南京理工大学信息管理系)
Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims
University of Chinese Academy of Sciences(中国科学院大学);Key Lab of Data Engineering and Knowledge Engineering, Renmin University of China(中国人民大学数据工程与知识工程重点实验室)
之前经过事实核查的虚假声明仍然可以在社交媒体上传播。为了减缓其持续蔓延,检测先前经过事实核查的说法是必不可少的。给定一个声明,现有的工作集中于通过对BM 25检索到的候选事实检查文章(FC-文章)进行重新排序来提供检测的证据。然而,这些性能可能是有限的,因为它们忽略了FC-文章的以下特征:(1)经常引用声明来描述检查的事件,提供语义之外的词汇信息;(2)用于引入或揭穿声明的句子模板在文章中很常见,提供模式信息。忽略这两个方面的模型只利用语义相关性,可能会被描述相似但不相关事件的句子误导。在本文中,我们提出了一种新的reranker,MTM(记忆增强的Transformers for Matching)排名FC文章使用的事件(词汇和语义)和模式信息选择的关键句。对于事件信息,我们提出了一个ROUGE引导的Transformer,它是用ROUGE回归进行微调的。对于模式信息,我们生成用于与句子匹配的模式向量。通过融合事件和模式信息,我们选择关键句来代表一篇文章,然后预测文章是否使用声明,关键句和模式对给定的声明进行事实检查。在两个真实数据集上的实验表明,MTM优于现有的方法。人工评估证明,MTM可以捕捉关键句子进行解释。代码和数据集位于https://github.com/ICTMCG/MTM。
Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
Research Laboratory in Algebra Numbers theory and Intelligent Systems(代数数论与智能系统研究实验室);CNRS(法国国家科学研究中心);Bordeaux INP(波尔多国立高等工程技术学院);LaBRI(波尔多计算机科学实验室);Laboratory LIG(LIG实验室)