Joint Models for Answer Verification in Question Answering Systems
This improves answer accuracy for QA systems, but is incremental as it builds on existing AS2 models.
The paper tackles the problem of verifying correct answers among top candidates in retrieval-based QA systems by modeling inter-answer relationships, achieving new state-of-the-art results on WikiQA, TREC-QA, and a real-world dataset.
This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that a critical step to effectively exploit an answer set regards modeling the interrelated information between pair of answers. For this purpose, we build a three-way multi-classifier, which decides if an answer supports, refutes, or is neutral with respect to another one. More specifically, our neural architecture integrates a state-of-the-art AS2 model with the multi-classifier, and a joint layer connecting all components. We tested our models on WikiQA, TREC-QA, and a real-world dataset. The results show that our models obtain the new state of the art in AS2.