[Most-ai-contest] About the Training/Testing Data for the Aggregation Module

[kysu]

OK. Thanks for the checking. Please let me know once you find out there is a benchmark answer which violates the specified rule of output formatting.

 

KY

 

From: 謝尊安 [mailto:pups003c at gmail.com] 
Sent: Tuesday, December 3, 2019 6:16 PM
To: Most-ai Contest <Most-ai-contest at iis.sinica.edu.tw>; kysu at iis.sinica.edu.tw
Subject: Re: [Most-ai-contest] About the Training/Testing Data for the Aggregation Module

 

Dear Dr. Su,

 

No unmatched unit of questions and answers found in version 1.3.

 

Regards,

謝尊安

 

On Mon, Dec 2, 2019 at 8:39 AM 江侑倫 <chiangyulun0914 at iis.sinica.edu.tw <mailto:chiangyulun0914 at iis.sinica.edu.tw> > wrote:

Dear Dr. Chang,

 

Enclose please find the attachments of dispatcher layer prediction, esp. for amode prediction.

 

Thanks.  

 

江侑倫

自然語言理解實驗室

中央研究院資訊科學研究所

Yu-Lun Chiang

Natural Language Understanding Lab

Institute of Information Science, Academia Sinica
Mobile: +886-975279013 (Taiwan)

 

 

江侑倫 <chiangyulun0914 at iis.sinica.edu.tw <mailto:chiangyulun0914 at iis.sinica.edu.tw> > 於 2019年11月29日 週五 上午8:59寫道：

Dear Dr. Chang,

 

Enclose please find the attachments of dispatcher layer prediction.

 

Thanks.

 

江侑倫

自然語言理解實驗室

中央研究院資訊科學研究所

Yu-Lun Chiang

Natural Language Understanding Lab

Institute of Information Science, Academia Sinica
Mobile: +886-975279013 (Taiwan)

 

 

江侑倫 <chiangyulun0914 at iis.sinica.edu.tw <mailto:chiangyulun0914 at iis.sinica.edu.tw> > 於 2019年11月28日 週四 下午4:39寫道：

Dear Dr. Chang,

 

Enclose please find the attachments of yes-no module prediction.

Thanks. 

 

江侑倫

自然語言理解實驗室

中央研究院資訊科學研究所

Yu-Lun Chiang

Natural Language Understanding Lab

Institute of Information Science, Academia Sinica
Mobile: +886-975279013 (Taiwan)

 

 

張光瑜 <simonc at iis.sinica.edu.tw <mailto:simonc at iis.sinica.edu.tw> > 於 2019年11月27日 週三 上午9:58寫道：

Dear all,

As I mentioned yesterday, if you are working on answer generating 
modules, please sent me your early results if you have any.
Please use the datasets in FGC_Release_1.2. For the output format, 
please use the following one based on FGC_Questions_S7_1.json, that is:
[
     {
         "DID": "document id",
         "QUESTIONS": [
             {
                 "QID": "question id",
                 "AMODE": {
                     "answer mode": {
                         "ACAND": [
                             {
                                 "SCORE": (confidence score),
                                 "ATEXT": "answer text",
                                 "AMODULE": "answer generating module"
                                 "ATOKEN": [
                                     {
                                         "text": "token text",
                                         "start": (index, -1 if not in 
the passage)
                                     },
                                     ...
                                 ]
                             },
                             ...
                         ]
                     }
                 }
             },
             ...
         ]
     },
     ...
]
Notice that there is an additional "AMODULE" field in the "ACAND" list.
Thank you for all your help.

Regards,
張光瑜

_______________________________________________
Most-ai-contest mailing list
Most-ai-contest at iis.sinica.edu.tw <mailto:Most-ai-contest at iis.sinica.edu.tw> 
https://www.iis.sinica.edu.tw/mailman/listinfo/most-ai-contest

_______________________________________________
Most-ai-contest mailing list
Most-ai-contest at iis.sinica.edu.tw <mailto:Most-ai-contest at iis.sinica.edu.tw> 
https://www.iis.sinica.edu.tw/mailman/listinfo/most-ai-contest

-- 

Tsun-An Hsieh

tel:       <tel:+886%20975%20329%20907> +886 975 329907

email:   <mailto:pups003c at gmail.com> pups003c at gmail.com

Institute of Networking and Multimedia, CSIE, National Taiwan University, Taiwan

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.iis.sinica.edu.tw/pipermail/most-ai-contest/attachments/20191203/422dac76/attachment.html>