Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification

CONLL 2017 Rebecca SharpMihai SurdeanuPeter JansenMarco A. Valenzuela-Esc{\'a}rcegaPeter ClarkMichael Hammond

For many applications of question answering (QA), being able to explain why a given model chose an answer is critical. However, the lack of labeled data for answer justifications makes learning this difficult and expensive... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Question Answering AI2 Kaggle Dataset OUR APPROACH [email protected] 54.0 # 4
Question Answering AI2 Kaggle Dataset IR Baseline [email protected] 47.2 # 1
Question Answering AI2 Kaggle Dataset IR++ [email protected] 50.7 # 3
Question Answering AI2 Kaggle Dataset Our Approach w/o IR [email protected] 50.54 # 2