Computerized Intelligence Systems Laboratory, Department of Computer Engineering, University of Tabriz(计算机工程系计算机智能系统实验室,大不里士大学);Department of Computer Engineering, University of Tabriz(计算机工程系,大不里士大学)
Keyword extraction is the process of identifying the words or phrases that express the main concepts of text to the best of one's ability. Electronic infrastructure creates a considerable amount of text every day and at all times. This massive volume of documents makes it practically impossible for human resources to study and manage them. Nevertheless, the need for these documents to be accessed efficiently and effectively is evident in numerous purposes. A blog, news article, or technical note is considered a relatively long text since the reader aims to learn the subject based on keywords or topics. Our approach consists of a combination of two models: graph centrality features and textural features. The proposed method has been used to extract the best keyword among the candidate keywords with an optimal combination of graph centralities, such as degree, betweenness, eigenvector, closeness centrality and etc, and textural, such as Casing, Term position, Term frequency normalization, Term different sentence, Part Of Speech tagging. There have also been attempts to distinguish keywords from candidate phrases and consider them on separate keywords. For evaluating the proposed method, seven datasets were used: Semeval2010, SemEval2017, Inspec, fao30, Thesis100, pak2018, and Wikinews, with results reported as Precision, Recall, and F- measure. Our proposed method performed much better in terms of evaluation metrics in all reviewed datasets compared with available methods in literature. An approximate 16.9% increase was witnessed in F-score metric and this was much more for the Inspec in English datasets and WikiNews in forgone languages.
Improving Performance of Automatic Keyword Extraction (AKE) Methods Using PoS-Tagging and Enhanced Semantic-Awareness
Institute of Cyber Security for Society (iCSS) & School of Computing(社会网络安全研究所(iCSS)及计算机学院);University of Kent(肯特大学);Shanghai Jiao Tong University(上海交通大学)
Unsupervised Keyword Extraction from Polish Legal Texts
Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw(华沙大学跨学科数学与计算建模中心);Faculty of Electronics and Information Technology, Warsaw University of Technology(华沙理工大学电子与信息技术学院)
YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
Stellenbosch University(斯泰伦博斯大学);University Politehnica of Bucharest(布加勒斯特理工大学)
视觉接地语音(VGS)模型在与未标记的口头字幕配对的图像上进行训练。这种模型可以用于在不可能获得标记数据的环境中构建语音系统,例如用于记录非书面语言。然而,大多数VGS研究都是用英语或其他高资源语言进行的。本文试图弥补这一缺陷。我们收集并发布了一个新的单扬声器数据集的音频字幕为6 k Flickr图像在Yorkebá-一个真正的低资源语言讲尼日利亚。我们训练一个基于注意力的VGS模型,其中图像自动标记有英语视觉标签,并与Yorkebá话语配对。这使得跨语言的关键字本地化:一个书面的英语查询被检测到,并在Yorkebá语音定位。为了量化较小数据集的影响,我们将其与在类似和更多数据上训练的英语系统进行了比较。我们希望这个新的数据集将刺激对真正的低资源语言使用VGS模型的研究。
RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation
National University of Science and Technology POLITEHNICA Bucharest(布加勒斯特理工国立科学技术大学);National Institute for Research and Development in Informatics - ICI Bucharest(布加勒斯特国家信息学研究与发展研究所);Paris 1 Panthéon-Sorbonne University(巴黎第一大学先贤祠-索邦大学);University of Bucharest(布加勒斯特大学)
A semi-automatic method for document classification in the shipping industry
IIT Kharagpur(印度理工学院卡拉格普尔分校);Birla Institute of Technology and Science, Pilani(贝拉理工科学与 pilani 学院);GradValley DataScience(GradValley 数据科学公司);Emulya Fintech PTE LTD(Emulya 金融科技私人有限公司);Singapore Government Judiciary(新加坡政府司法机构)
Improved Visually Prompted Keyword Localisation in Real Low-Resource Settings
Electrical and Electronic Engineering(电气与电子工程);Stellenbosch University(斯泰伦博斯大学);National University of Science and Technology(国家科学与技术大学);\textsc{Politehnica} Bucharest(布加勒斯特理工大学)
VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search
Yahoo Research(雅虎研究院)
许多在线库存图像库提供高质量但版权免费的图像用于营销活动。为了帮助广告客户在导航这样的第三方图书馆,我们研究的问题,自动获取相关的广告图像的广告文本(通过一个简短的文本查询图像)。出于我们的观察记录的数据上的广告图像搜索查询(给定的广告文本),我们制定了一个关键字提取问题,从广告文本(或其增强版本)中提取的关键字作为广告图像查询。在这种情况下,我们提出了VisualTextRank:一种无监督的方法,(i)使用语义相似的广告来增强输入广告文本,以及(ii)从增强的广告文本中提取图像查询。VisualTextRank建立在基于图的上下文提取(特别是有偏见的TextRank)的先前工作基础上,通过利用类似广告的文本和图像来更好地提取关键字,并使用广告商类别特定的偏见与BERCE-BERT嵌入。使用从Verizon Media Native(Yahoo Gemini)广告平台的库存图像搜索功能为入职广告客户收集的数据,我们证明了VisualTextRank与竞争性关键字提取基线相比的优越性(包括$11\%$准确性提升超过有偏见的TextRank)。对于股票图像库仅限于英语查询的情况下,我们显示了VisualTextRank对多语言广告(翻译为英语)的有效性,同时利用语义相似的英语广告。使用简化版本的VisualTextRank进行的在线测试导致库存图片搜索的使用量增加了28.7%,Ver…