Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPs
This work aims to improve the efficiency of information retrieval for users on CQA platforms by providing a concise and representative set of answers, rather than a ranked list.
This paper addresses the problem of information overload in community-based question answering (CQA) platforms by proposing a new task: extracting a diverse and non-redundant set of answers. The method utilizes determinantal point processes (DPPs) with BERT to calculate answer importance and similarity, outperforming several baselines on a Japanese CQA dataset.
In community-based question answering (CQA) platforms, it takes time for a user to get useful information from among many answers. Although one solution is an answer ranking method, the user still needs to read through the top-ranked answers carefully. This paper proposes a new task of selecting a diverse and non-redundant answer set rather than ranking the answers. Our method is based on determinantal point processes (DPPs), and it calculates the answer importance and similarity between answers by using BERT. We built a dataset focusing on a Japanese CQA site, and the experiments on this dataset demonstrated that the proposed method outperformed several baseline methods.