We propose Group-Level Answer Triggering (GAT), an end-to-end deep neural network framework which is trained by a novel group-level objective function and directly optimizes the answer triggering performance. More details are in the paper "An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective" published in EMNLP'17.
We propose Group-Level Answer Triggering (GAT), an end-to-end deep neural network framework which is trained by a novel group-level objective function and directly optimizes the answer triggering performance.
For more details, please see https://github.com/jiez-osu/answer-triggering