Thanks!

I don't see the document, Xinxiong probably replied and sent it directly to
you Chelsy?

On related topic: I started to experiment with the java implementation of
jieba (see the last comment in https://phabricator.wikimedia.org/T151743)
The Zero result rate dropped to 17.5% instead of 10% which sounds a bit
more consistent with our average. Sadly I can't really judge on the
quality. This was also a very quick experiment where I had to get rid of
some other features we use like unicode normalization.

Thank you!

On Mon, Dec 5, 2016 at 6:49 AM, Chelsy Xie <[email protected]> wrote:

> Thank you!!!
>
> On Sun, Dec 4, 2016 at 3:59 AM, 陈新雄 <[email protected]> wrote:
>
>> Hi all:
>>
>>     Please find attached the document of THULAC.
>>
>>     If you have any questions, contact me ASAP.
>>
>> Regards,
>> Xinxiong
>>
>> 2016-12-02 9:50 GMT+08:00 陈新雄 <[email protected]>:
>>
>>> Hi all,
>>>
>>>     I'm Xinxiong Chen, a PhD student from Tsinghua University. I
>>> graduate from THU NLP&CSS lab (Tsinghua University Natural Language
>>> Processing and Computational Social Science Lab) this July. I'm the main
>>> developer of THULAC and I will translate THULAC's documentation into
>>> English and offer technical support.
>>>
>>>     I know from Chelsy that most of you are using python so I will
>>> translate the document of python version.
>>>
>>>     Chelsy and I are classmates in high school and we are friends from
>>> then. So don't hesitate to contact me if you have any questions.
>>>
>>> Regards,
>>> Xinxiong
>>>
>>>
>>>
>>> 2016-12-02 9:16 GMT+08:00 Chelsy Xie <[email protected]>:
>>>
>>>> Hello everyone,
>>>>
>>>> I'm very happy to introduce you to Xinxiong Chen <[email protected]>,
>>>> the main developer of THULAC <https://github.com/thunlp/THULAC-Python>
>>>> and a CS PhD student at Tsinghua University. :)
>>>>
>>>> Discovery team is looking for a new Chinese tokenizer and THULAC
>>>> <https://github.com/thunlp/THULAC-Python> may be helpful. Here
>>>> <https://github.com/thunlp/THULAC-Python#代表分词软件的性能对比> is a comparison
>>>> between THULAC and other Chinese tokenizers (jieba, LTP-3.2.0 and ICTCLAS).
>>>> It's very kind of Xinxiong to help us to translate THULAC's documentation
>>>> into English and offer technical support.
>>>>
>>>> Thank you very much Xinxiong!
>>>>
>>>> Cheers,
>>>> Chelsy
>>>>
>>>>
>>>
>>>
>>> --
>>> 陈 新雄(Chen Xinxiong)
>>>
>>> Department of Computer Science and Technology
>>> Tsinghua University
>>>
>>> Beijing 100084, China
>>>
>>
>>
>>
>> --
>> 陈 新雄(Chen Xinxiong)
>>
>> Department of Computer Science and Technology
>> Tsinghua University
>>
>> Beijing 100084, China
>>
>
>
> _______________________________________________
> discovery mailing list
> [email protected]
> https://lists.wikimedia.org/mailman/listinfo/discovery
>
>
_______________________________________________
discovery mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/discovery

Reply via email to