翻译动态:Transmart、微软NMT以及BasicCAT

腾讯发布人工智能辅助翻译,致敬人工翻译。

11 月 13 日,深圳 – 腾讯 AI Lab 发布了一款 AI 辅助翻译产品 ——「腾讯辅助翻译」(Transmart),可满足用户快速翻译的需求,用 AI 辅助人工翻译提高效率和质量。该产品由腾讯 AI Lab 的内部团队历时一年完成,采用了团队自研的人机交互式机器翻译技术,融合神经网络机器翻译、统计机器翻译、输入法、语义理解、数据挖掘等多项前沿技术,配合亿级双语平行数据,是一款人工智能辅助翻译互联网落地产品,可为用户提供实时智能翻译辅助,帮助用户更好更快地完成翻译任务。

1、内核是国内第一个公开的交互式机器翻译的互联网落地产品;
2、搭载了业内第一个公开的融合机器翻译的辅助翻译输入法。该产品融合了人工智能和传统辅助翻译技术,为用户提供更便捷、流畅的人工翻译体验。
3、千万级专业术语、亿级例句参照。腾讯 AI Lab 从几百 TB 的互联网文本中挖掘了数千万的专业术语翻译和亿级双语例句提供给用户作为翻译参考信息。
4、辅助翻译 API 与定制化服务。为合作伙伴开放交互式机器翻译、辅助翻译输入法、个性化机器翻译 API、定制化机器翻译等多个应用程序接口,提供定制化服务。


微软发布新一代神经机器翻译技术

2018年初,微软宣布推出第一个机器翻译系统,用于新闻的中译英,其质量和准确度与人类媲美。今天,Microsoft Translator将这些研究成果投产,并发布了新的中英、德英双向翻译系统,提高了翻译质量,扩充了应用场景。

基于使用行业标准测试集的人工评估发现,整体质量提高了11%。此项改进基于与之前的生产API对比。

这些改进是研究系统的结果,这些研究系统在今年早些时候在一组常用的新闻报道上实现了人类效果般的翻译,且现在已经兼容了生产API。这其中包括下一代的神经网络架构和双重学习。

微软举了几个中英文翻译质量改进例子。

新的系统已用于所有Microsoft Translator应用程序、插件、Office、必应翻译以及API,适用于企业和开发人员。

2019年初将推出基于此高级翻译系统的其他语言。

Microsoft Translator Blog: Microsoft Translator releases next-generation Neur…


上周五推荐的BasicCAT今天又分别在Mac和Windows上做了测试,测试的结果是其实这个工具还是挺好用的。

但是在配置的过程中还是需要花费一些功夫,尤其是对于很多翻译出身的技术小白来说会遇到各种问题(这并非产品本身的bug),比如用于语言检查的LanguageTool的配置,再比如用于交互式机器翻译的斯坦福自然语言处理工具Start CoreNLP Server的配置(很多时候下载、配置后利用BasicCAT用户文档里提供的测试地址进行测试发现服务器无法运行,衰)。很多同学前天反应软件频繁闪退,或者无法打开source源翻译文件,这里需要注意2个地方:1.Basic并不能够像Trados一样直接对单文档文件进行翻译处理,需要新建项目并且保存后再进行翻译文件的导入(新建项目需要注意语言方向);2.BasicCAT目前支持的文档格式比较有限(比如不能直接对word格式的处理):text、idml、xliff、pdf等。pdf目前仍然需要借助basic内嵌工具进行文本的抓取或者外部OCR工具处理。

个人测试过程中,机器翻译api的配置、划词取义、在线词典、以及word导出、双语对照这些高阶功能,以及入门功能中的记忆库、术语库的操作,和片段合并、分割等,则非常的顺利。 

Proz上开发者和外国译者针对BasicCAT的讨论

开发者目前也在bilibili同步释出学习教程


BasicCAT是一款开源的计算机辅助翻译软件,旨在为译员提供简单实用的翻译工具。取名BasicCAT,一是因为它简单易用,二是因为它使用Basic语言编写,普通人花上一段时间学习后也能掌握,从而在BasicCAT源代码的基础上修改出适合自己需要的软件。

软件具有以下功能:

翻译记忆
术语管理
语言检查
划词取义
快速填充
自动更正
交互式机器翻译
导出Word供外部审校
导出双语段落对照文件
句段分割与合并
调用多种在线词典
常见机器翻译服务的API调用
支持利用翻译记忆与机器翻译进行全文预翻译
支持常见源文件格式:txt, idml, xliff, gettext po
支持翻译记忆标准TMX、术语管理标准TBX和句段分割标准SRX
使用Git进行版本控制

软件下载:下载 – BasicCAT
入门和进阶操作学习:BasicCAT 使用手册

BasicCAT支持 Windows,Macintosh,Linux 三个平台;软件支持多种文件格式,支持机器翻译调用,支持多格式翻译记忆库和术语库,支持译文质量检查,支持导出双语对照文件,提供详细的使用帮助文件。

据说软件由北京大学2017级CAT学生开发,开发者大学本科是英语专业,硕士在北京大学软件与微电子学院学习计算机辅助翻译。英雄出少年!

大家如果在使用过程中有问题或者建议,可以在GitHub给开发者提issue

《翻译动态:Transmart、微软NMT以及BasicCAT》有16个想法

  1. you’re actually a just right webmaster. The site loading
    pace is incredible. It seems that you are doing any distinctive trick.

    Furthermore, The contents are masterpiece. you have performed a magnificent job in this matter!

  2. Very good blog! Do you have any recommendations for aspiring writers?
    I’m planning to start my own site soon but I’m a little lost
    on everything. Would you suggest starting with a free
    platform like WordPress or go for a paid option? There are so many choices out there that I’m
    totally overwhelmed .. Any tips? Appreciate it!

  3. Hi, I do believe this is an excellent site. I stumbledupon it 😉
    I will come back yet again since i have book-marked it.
    Money and freedom is the best way to change, may you be rich
    and continue to help others.

  4. Hello! I could have sworn I’ve been to this blog before but
    after looking at many of the articles I realized it’s new to me.
    Anyways, I’m definitely happy I discovered it and I’ll be bookmarking it and checking back regularly!

  5. This is the right website for anyone who wants to understand
    this topic. You know a whole lot its almost hard to argue with you (not that I actually would want to…HaHa).
    You definitely put a fresh spin on a topic that has been discussed for years.
    Wonderful stuff, just great!

  6. Nice weblog here! Also your website lots up very fast!
    What web host are you using? Can I am getting your affiliate link for your host?
    I desire my site loaded up as fast as yours lol

  7. Cbd oil that works 2020
    Hi there! This post could not be written much better!

    Looking at this article reminds me of my previous roommate!
    He continually kept preaching about this. I am going to send this information to him.

    Pretty sure he will have a very good read. I appreciate you for sharing!
    best rated cbd oil http://j.mp/3drY6lE cbd oil that works 2020 http://j.mp/3drY6lE

  8. Cbd oil that works 2020
    Hello! This is kind of off topic but I need some help from an established blog.
    Is it very hard to set up your own blog? I’m not very techincal but I can figure things out pretty fast.
    I’m thinking about creating my own but I’m not sure where to begin. Do you have any points or suggestions?
    Many thanks best cbd oil for pain http://tinyurl.com/cbd-oil-that-works-2020 cbd oil that works
    2020 http://tinyurl.com/cbd-oil-that-works-2020

  9. What’s up to every one, the contents present at this website are in fact awesome for
    people experience, well, keep up the good work fellows.

  10. Very nice post. I just stumbled upon your blog and wished to
    mention that I have truly loved browsing your weblog posts.
    After all I’ll be subscribing for your feed and I hope you write again very soon!

  11. Hi there! Would you mind if I share your blog with my twitter group?
    There’s a lot of folks that I think would really appreciate
    your content. Please let me know. Many thanks

  12. Right here is the perfect web site for anyone who hopes to understand this topic.

    You know so much its almost tough to argue with you (not
    that I actually will need to…HaHa). You definitely put a fresh spin on a topic
    that’s been written about for decades. Excellent stuff,
    just wonderful!

发表评论

电子邮件地址不会被公开。 必填项已用*标注