LiCQA : A Lightweight Complex Question Answering System
This addresses the challenge of complex QA for users needing efficient, resource-light systems, though it appears incremental as it builds on existing QA approaches.
The paper tackles the problem of answering complex questions requiring information from multiple documents by introducing LiCQA, an unsupervised QA model based on corpus evidence, which significantly outperforms two state-of-the-art systems on benchmark data with reduced latency.
Over the last twenty years, significant progress has been made in designing and implementing Question Answering (QA) systems. However, addressing complex questions, the answers to which are spread across multiple documents, remains a challenging problem. Recent QA systems that are designed to handle complex questions work either on the basis of knowledge graphs, or utilise contem- porary neural models that are expensive to train, in terms of both computational resources and the volume of training data required. In this paper, we present LiCQA, an unsupervised question answer- ing model that works primarily on the basis of corpus evidence. We empirically compare the effectiveness and efficiency of LiCQA with two recently presented QA systems, which are based on different underlying principles. The results of our experiments show that LiCQA significantly outperforms these two state-of-the-art systems on benchmark data with noteworthy reduction in latency.