LiCQA : A Lightweight Complex Question Answering System
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914350831239168 |
|---|---|
| author | Saha, Sourav Roy, Dwaipayan Mitra, Mandar |
| author_facet | Saha, Sourav Roy, Dwaipayan Mitra, Mandar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22182 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LiCQA : A Lightweight Complex Question Answering System Saha, Sourav Roy, Dwaipayan Mitra, Mandar Computation and Language Information Retrieval 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. |
| title | LiCQA : A Lightweight Complex Question Answering System |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2602.22182 |