ESL Assistant News & Notes

New version with better coverage!

A new version of the system was deployed today! What you should see is a good deal more suggested corrections where the system did not flag errors before. If you're interested in technical details: under the covers, our algorithm for finding good correction

Latest bug fixes and preview of upcoming changes

After we deployed our new UI, we received some user feedback about truncated text passages when the Outlook plugin is used. It took us a while to figure out the details, but this problem should now be fixed. We also found some text rendering problems

The ESL Assistant Has a New Look

The ESL Assistant, the MSR Natural Language Processing Group's prototype proofing tool for people who write English as a second or foreign language, has been given a makeover. Visitors to the site at http://www.eslassistant.com will now see a page that

试试ESL助理

工作以来几乎天天要用英语写点东西，但对很多用法还是没有底。于是我常常将一些吃不准的英语用法当作检索词，在 互联网上看看是否有很多相同的用法 。基于这些经验，我和 微软研究院的同事们开发了一个英语自动校对原型系统，叫 ESL 助理。该系统的目标用户便是像我一样的，不以英语为母语的英语用户。ESL助理采用一些统计语言模型检测出英语书写中的问题并提出修改建议。用户可以通过该系统提供的互联网例句检索工具确认所提供修改建议。 自己用了一下，感觉还不错。有兴趣的话，你也来试试。 ESL 助理 http://www.eslassistant.com/

... a modest goal ...

... or (for those who understand the cultural reference here): all your errors are not belong to us. Well, we all (i.e. us non-native speakers of English, myself as a native German included) would like a tool that could just take what we write and turn

The Microsoft Research ESL Assistant Prototype is Live

The Natural Language Processing Group in Microsoft Research is pleased to announce that its ESL Assistant is now available on the World Wide Web via a link at http://www.eslassistant.com. A prototype writing assistance service designed for people who have learned English as a second or foreign language, the ESL Assistant uses statistical models to suggest corrections for a number of common learner error patterns that are not currently supported by the proofing tools in Microsoft Office products. The service also tries to help users judge the whether a suggestion truly represents an improvement by showing real-life examples returned by a web search. We hope that both learners of English and TEFL/TESL professionals will experiment with this service and find it useful.