Nowadays, individuals can be overwhelmed by a huge number of documents being present in daily life. Capturing the necessary details is often a challenge. Therefore, it is rather important to summarize documents to obtain the main information quickly. There currently exist automatic approaches to this task, but their quality is often not properly assessed. State-of-the-art metrics rely on human-generated summaries as a reference for the evaluation. If no reference is given, the assessment will be challenging. Therefore, in the absence of human-generated reference summaries, we investigated an alternative approach to how machine-generated summaries can be evaluated. For this, we focus on the original text or document to retrieve a metric that allows a direct evaluation of automatically generated summaries. This approach is particularly helpful in cases where it is difficult or costly to find reference summaries. In this paper, we present a novel metric called Summary Score without Reference—SUSWIR—which is based on four factors already known in the text summarization community: Semantic Similarity, Redundancy, Relevance, and Bias Avoidance Analysis, overcoming drawbacks of common metrics. Therefore, we aim to close a gap in the current evaluation environment for machine-generated text summaries. The novel metric is introduced theoretically and tested on five datasets from their respective domains. The conducted experiments yielded noteworthy outcomes, employing the utilization of SUSWIR.
如今，个人在日常生活中可能会被大量文件淹没。捕捉必要的细节往往是一项挑战。因此，对文件进行摘要以快速获取主要信息就显得相当重要。目前有一些自动方法可以完成这项任务，但其质量往往得不到适当的评估。最先进的衡量标准依赖于人工生成的摘要作为评估参考。如果没有参照物，评估工作将面临挑战。因此，在没有人工生成的参考摘要的情况下，我们研究了另一种方法来评估机器生成的摘要。为此，我们将重点放在原始文本或文档上，以检索可直接评估自动生成摘要的指标。这种方法尤其适用于难以找到参考摘要或成本较高的情况。在本文中，我们提出了一种名为 "无参考摘要得分"（Summary Score without Reference-SUSWIR）的新指标，它基于文本摘要界已知的四个因素：该指标基于文本摘要界已知的四个因素：语义相似性、冗余性、相关性和避免偏差分析，克服了普通指标的缺点。因此，我们的目标是填补当前机器生成文本摘要评估环境中的空白。我们从理论上介绍了这种新的度量方法，并在各自领域的五个数据集上进行了测试。利用 SUSWIR 进行的实验取得了显著的成果。
{"title":"Who Needs External References?—Text Summarization Evaluation Using Original Documents","authors":"Abdullah Al Foysal, Ronald Böck","doi":"10.3390/ai4040049","DOIUrl":"https://doi.org/10.3390/ai4040049","url":null,"abstract":"Nowadays, individuals can be overwhelmed by a huge number of documents being present in daily life. Capturing the necessary details is often a challenge. Therefore, it is rather important to summarize documents to obtain the main information quickly. There currently exist automatic approaches to this task, but their quality is often not properly assessed. State-of-the-art metrics rely on human-generated summaries as a reference for the evaluation. If no reference is given, the assessment will be challenging. Therefore, in the absence of human-generated reference summaries, we investigated an alternative approach to how machine-generated summaries can be evaluated. For this, we focus on the original text or document to retrieve a metric that allows a direct evaluation of automatically generated summaries. This approach is particularly helpful in cases where it is difficult or costly to find reference summaries. In this paper, we present a novel metric called Summary Score without Reference—SUSWIR—which is based on four factors already known in the text summarization community: Semantic Similarity, Redundancy, Relevance, and Bias Avoidance Analysis, overcoming drawbacks of common metrics. Therefore, we aim to close a gap in the current evaluation environment for machine-generated text summaries. The novel metric is introduced theoretically and tested on five datasets from their respective domains. The conducted experiments yielded noteworthy outcomes, employing the utilization of SUSWIR.","PeriodicalId":503525,"journal":{"name":"AI","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139271112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Technical advancements within the subject of artificial intelligence (AI) leads towards development of human-like machines, able to operate autonomously and mimic our cognitive behavior. The progress and interest among managers, academics and the public has created a hype among many industries, and many firms are investing heavily to capitalize on the technology through business model innovation. However, managers are left with little support from academia when aiming to implement AI in their firm’s operations, which leads to an increased risk of project failure and unwanted results. This paper aims to provide a deeper understanding of AI and how it can be used as a catalyst for business model innovation. Due to the increasing range and variety of the available published material, a literature review has been performed to gather current knowledge within AI business model innovation. The results are presented in a roadmap to guide the implementation of AI to firm’s operations. Our presented findings suggest four steps when implementing AI: (1) understand AI and organizational capabilities needed for digital transformation; (2) understand current BM, potential for BMI, and business ecosystem role; (3) develop and refine capabilities needed to implement AI; and (4) reach organizational acceptance and develop internal competencies.
{"title":"Implementation of Artificial Intelligence (AI): A Roadmap for Business Model Innovation","authors":"W. Reim, Josef Åström, Oliver Eriksson","doi":"10.3390/ai1020011","DOIUrl":"https://doi.org/10.3390/ai1020011","url":null,"abstract":"Technical advancements within the subject of artificial intelligence (AI) leads towards development of human-like machines, able to operate autonomously and mimic our cognitive behavior. The progress and interest among managers, academics and the public has created a hype among many industries, and many firms are investing heavily to capitalize on the technology through business model innovation. However, managers are left with little support from academia when aiming to implement AI in their firm’s operations, which leads to an increased risk of project failure and unwanted results. This paper aims to provide a deeper understanding of AI and how it can be used as a catalyst for business model innovation. Due to the increasing range and variety of the available published material, a literature review has been performed to gather current knowledge within AI business model innovation. The results are presented in a roadmap to guide the implementation of AI to firm’s operations. Our presented findings suggest four steps when implementing AI: (1) understand AI and organizational capabilities needed for digital transformation; (2) understand current BM, potential for BMI, and business ecosystem role; (3) develop and refine capabilities needed to implement AI; and (4) reach organizational acceptance and develop internal competencies.","PeriodicalId":503525,"journal":{"name":"AI","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141207173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：