Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification
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. Here we propose an approach that uses answer ranking as distant supervision for learning how to select informative justifications, where justifications serve as inferential connections between the question and the correct answer while often containing little lexical overlap with either. We propose a neural network architecture for QA that reranks answer justifications as an intermediate (and human-interpretable) step in answer selection. Our approach is informed by a set of features designed to combine both learned representations and explicit features to capture the connection between questions, answers, and answer justifications. We show that with this end-to-end approach we are able to significantly improve upon a strong IR baseline in both justification ranking (+9{\%} rated highly relevant) and answer selection (+6{\%} P@1).
PDF Abstract
Datasets
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Question Answering | AI2 Kaggle Dataset | OUR APPROACH | P@1 | 54.0 | # 4 | |
| Question Answering | AI2 Kaggle Dataset | IR++ | P@1 | 50.7 | # 3 | |
| Question Answering | AI2 Kaggle Dataset | Our Approach w/o IR | P@1 | 50.54 | # 2 | |
| Question Answering | AI2 Kaggle Dataset | IR Baseline | P@1 | 47.2 | # 1 |
