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

[張光瑜]

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