TAUS and Intento Collaborate for the Intento 2021 State of Machine Translation Report

翻译自动化用户协会(Translation Automation User Society,简称TAUS)和Intento合作完成Intento 2021机器翻译状况报告

2021-10-07 17:50 TAUS

本文共706个字,阅读需8分钟

阅读模式 切换至中文

Amsterdam, 7 October 2021 TAUS collaborates with Intento for the Intento 2021 State of Machine Translation Report by providing high-quality, domain-specific language datasets to be used in their MT tests. With this report, Intento, the leading AI integration platform, provides those working in and around the MT landscape an in-depth analysis of the current vendors and best strategies to successfully leverage their offerings. The report is based on the tests conducted using test datasets offered by TAUS, the language data network, offering the largest industry-shared repository of data, deep know-how in language engineering, and a network of Human Language Project workers around the globe. You can download the report here. The report aims to provide an expert vision of the constantly-changing MT landscape to save internationally-facing businesses both human and financial capital. The 2021 edition delivers an extensive evaluation to help you choose the best-fit MT engines for your language pair and industry sector. The report evaluated the performance of different MT engines across 7 industries (Education, Finance, Healthcare, Hospitality, Legal, Entertainment, and General) and 13 language key pairs, using the latest data on 24 commercial MT engines including Alibaba eCommerce and General, Amazon, Apptek, Baidu, DeepL, Elia, Globalese, Google, GTCom, IBM Watson, Microsoft, ModernMT, Naver, Kawamura / NICT, Pangeanic, PROMT, Rozetta, Systran, Tilde, Tencent, Yandex, Youdao, and XL8. “Working with MT is like living on an erupting volcano. We had 16,000 language pairs available from 34 MT providers just a year ago, and today it’s about 100,000 from 46. We don't have datasets to evaluate them all, but by working with TAUS we get a look into 13 language pairs and 7 domains", says Konstantin Savenkov, Intento CEO. "The level of quality we see from stock models in 2021 is unprecedented. However, real-world business applications demand even more, and simply knowing the best stock model is not enough to succeed with MT. Make sure you have domain adaptation, glossaries, tone of voice control, and other tools on your belt." Savenkov continues, "this year, together with TAUS, we had a particular focus on using high-quality domain-specific data. It took more time to prepare, but the results should be relevant to a wider audience and applicable to more use cases than before. One key highlight we see from this year is the emergence of new semantic similarity metrics, such as COMET". “The availability of high-quality, domain-specific language data has become ever so significant as AI-enabled automatic translation becomes more and more common. We believe the findings will provide guidance on which MT engines are best suitable for the users' requirements and, above all, demonstrate the value of high-quality, domain-specific data in increasing the quality of the final output,” says Jaap van der Meer, TAUS Director. About TAUS TAUS was founded in 2005 as a think tank with a mission to automate and innovate translation. Ideas transformed into actions. TAUS has become the one-stop language data shop, established through deep knowledge of the language industry, globally sourced community talent, and in-house NLP expertise. We create and enhance language data for the training of better, human-informed AI services. Our mission today is to empower global enterprises and their service and technology providers with data solutions that help them to communicate in all languages, faster, better, and more efficiently. For more information, visit https://www.taus.net/. About Intento Intento, the leading AI integration platform, helps global companies utilize the best-fit cognitive AI services and automate content creation (text synthesis), content transformation (between text, speech, and image), and content localization (machine translation), enabling enterprises to translate 20x more content on their existing budgets. This year, Intento was recognized as a 2021 Cool Vendor in Conversational and Natural Language Technologies by Gartner for its success in enhancing the supply chain of the global translation business. The Intento AI Hub gives global corporations direct, easy access to a multitude of MT engines (such as Amazon, Google AutoML, or Microsoft Cognitive Services) and seamlessly connects them with all of their business systems. Launched in 2017, Intento offers its patented, ISO-27001 and ISO-9001 certified platform to global companies across all industries, augmenting their Localization, Content Management, Customer Support, and Marketing Operations with AI. For more information, visit https://inten.to.
阿姆斯特丹,2021年10月7日 TAUS与Intento合作发布《2021年机器翻译状态报告》,为其MT测试提供高质量、领域特定的语言数据集。 通过这份报告,领先的人工智能集成平台Intento为从事MT领域工作的人员提供了对当前供应商的深入分析,以及成功利用其产品的最佳策略。该报告基于使用语言数据网络TAUS提供的测试数据集进行的测试。TAUS提供了最大的行业共享数据库,在语言工程方面拥有深厚的专业知识,以及全球范围内的人类语言项目(Human language Project)工作者网络。你可以在这里下载报告。 该报告旨在为不断变化的MT景观提供专家视角,以拯救面向国际的企业的人力和金融资本。2021版提供了广泛的评估,以帮助您选择最适合您的语言对和行业部门的MT引擎。该报告评估了7个行业(教育、金融、医疗保健、酒店、法律、娱乐和通用)和13个语言关键对的不同MT引擎的性能,使用了24个商业MT引擎的最新数据,包括阿里巴巴电子商务和通用、亚马逊、Apptek、百度、DeepL、Elia、Globalese、谷歌、GTCom、IBM Watson,微软,ModernMT, Naver, Kawamura / NICT, Pangeanic, PROMT, Rozetta, Systran, Tilde,腾讯,Yandex,有道,XL8。 “与MT一起工作就像生活在一座喷发的火山上。仅仅在一年前,我们从34个MT提供商那里获得了16,000种语言对,而今天,从46个MT提供商那里获得了大约100,000种语言对。Intento首席执行官康斯坦丁•萨文科夫表示:“我们没有数据集来评估所有这些模型,但通过与TAUS合作,我们可以看到13种语言对和7个领域。我们从2021年股票模型中看到的质量水平是前所未有的。”然而,现实世界的业务应用程序的要求甚至更高,仅仅知道最佳股票模型并不足以用MT取得成功。确保你的腰带上有领域适应,词汇表,声调控制和其他工具,“ Savenkov继续说道:“今年与TAUS一起,我们特别关注于使用高质量的领域特定数据。它需要花费更多的时间来准备,但是结果应该与更广泛的受众相关,并且比以前适用于更多的用例。今年我们看到的一个重要亮点是出现了新的语义相似度指标,比如COMET”。 TAUS主任Jaap van der Meer说,“随着人工智能自动翻译变得越来越普遍,获得高质量、特定领域的语言数据变得越来越重要。我们相信研究结果将为哪些MT发动机最适合用户的要求提供指导,最重要的是,证明了高质量、特定领域的数据在提高最终输出质量方面的价值,” 关于TAUS 翻译自动化用户协会,TAUS成立于2005年,是一个以自动化和创新翻译为使命的智库。想法变成了行动。TAUS已经成为一站式语言数据商店,建立在语言行业的深厚知识,全球资源社区人才和内部NLP专业知识。我们创建和增强语言数据,以培训更好的、人性化的人工智能服务。 我们今天的使命是为全球企业及其服务和技术供应商提供数据解决方案,帮助他们更快、更好、更有效地用所有语言进行沟通。了解更多资讯,请访问https://www.taus.net/。 关于Intento Intento是全球领先的人工智能集成平台,帮助全球企业利用最适合的认知人工智能服务和自动化内容创建(文本合成)、内容转换(文本、语音和图像之间)和内容本地化(机器翻译),使企业能够在现有预算的基础上翻译20倍以上的内容。 今年,Intento成功地加强了全球翻译业务的供应链,被Gartner评为2021年度会话和自然语言技术领域的酷供应商。Intento AI Hub可以让全球企业直接、方便地访问多种MT引擎(如Amazon、谷歌AutoML或Microsoft Cognitive Services),并将它们与所有业务系统无缝连接。 Intento于2017年推出,为全球所有行业的公司提供其ISO-27001和ISO-9001认证的专利平台,通过人工智能增强其本地化、内容管理、客户支持和营销运营。了解更多资讯,请访问https://inten.to。

以上中文文本为机器翻译,存在不同程度偏差和错误,请理解并参考英文原文阅读。

阅读原文