Performance Prediction for Multi-hop Question Answering

Abstract

In this thesis, we study the problem of performance prediction for open-domain multi-hop Question Answering (QA), where the task is to estimate the difficulty of evaluating a multi-hop question over a corpus. Despite the extensive research on predicting the performance of ad-hoc and QA retrieval models, there has been a lack of study on the estimation of the difficulty of multi-hop questions. The problem is challenging due to the multi-step nature of the retrieval process, potential dependency of the steps and the reasoning involved. To tackle this challenge, we propose multHP, a novel pre-retrieval method for predicting the performance of open-domain multi-hop questions. Our evaluation on one of the largest multi-hop QA dataset shows that the proposed model is a strong predictor of the performance of several modern QA systems, outperforming traditional single-hop query performance prediction methods. Furthermore, given the dynamic nature of information retrieval in multi-hop question answering, post-retrieval methods offer a more accurate means of measuring the difficulty of multi-hop questions compared to pre-retrieval methods. Thus, we present a post-retrieval method tailored for multi-hop question answering, highlighting the limitations of other methods proposed in the ad-hoc retrieval domain that may not be applicable in this specific context. We demonstrate that our approach can be effectively used to optimize the parameters of the systems, such as the number of documents to be retrieved, resulting in improved overall retrieval performance.