Multiple arguments of the same argument role

[PureLoveForyou]

Hi. I'm dealing with a dataset that has several argument roles, and each role might have multiple arguments. For example, '<arg1>, <arg2>, <arg3>, <arg4>, <arg5> has participate in an military activity on <arg6> ... ' In this sentence, arg1 to arg5 is the same role but different arguments, they are all the role 'countries'. And the problem is, each data in my dataset might have different number of 'countries'. In my example there are five countries which is arg1 to arg5, while in other data it might be just 3 countries which is arg1 to arg3 or just 1 countries. And I tried to use template like '<arg1>, <arg2>, <arg3>, <arg4>, <arg5> has participate in an military activity on <arg6> ... ', but I got pretty bad result, because it seems to be predicting a lot of '<arg> <arg> <arg>' and the result sentence looks absurd. If I use use template like '<arg1> has participate in an military activity on <arg2> ... ', the result is normal and acceptable, but in this way I can only predict a single one countries(arg1). Is there a way to deal with this? Thanks.

[raspberryice]

Are there also many cases of multiple argument values for the same role in your training dataset?

I would suggest that you experiment with different templates. What worked for me is to keep 1 placeholder in the empty template and use all arguments for the filled template during training. Assuming that A, B, C all on take the country role, for training you would have:

• Input: participated in an military activity. Output: A, B and C participated in an military activity ...
• Input: The countries that participated in military activity include . Output: The countries that participated in military activity include A, B and C.