LiCQA : A Lightweight Complex Question Answering System
2026-02-25 • Computation and Language
Computation and LanguageInformation Retrieval
AI summaryⓘ
The authors developed LiCQA, a question-answering system that can handle complex questions needing information from multiple documents, without needing expensive training. Unlike other recent systems that rely on knowledge graphs or large neural networks, LiCQA works mainly by looking directly at the text corpus. They tested LiCQA against two leading QA systems and found that it not only performed better but also responded faster. This shows that the authors created an effective and efficient way to answer complicated questions using less computational power.
Question AnsweringComplex QuestionsKnowledge GraphsNeural ModelsUnsupervised LearningCorpus EvidenceLatencyBenchmark Data
Authors
Sourav Saha, Dwaipayan Roy, Mandar Mitra
Abstract
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.