Lirong Yin¹, Lei Wang¹, Zhuohang Cai², Siyu Lu^2,*, Ruiyang Wang², Ahmed AlSanad³, Salman A. AlQahtani³, Xiaobing Chen⁴, Zhengtong Yin⁵, Xiaolu Li⁶, Wenfeng Zheng^2,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.1, pp. 771-786, 2024, DOI:10.32604/cmes.2024.052622 - 20 August 2024

Abstract Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems. However, with the constant evolution of algorithms, data, and computing power, the increasing size and complexity of these models have led to increased training costs and reduced efficiency. This study aims to minimize the inference time of such models while maintaining computational performance. It also proposes a novel Distillation model for PAL-BERT (DPAL-BERT), specifically, employs knowledge distillation, using the PAL-BERT model as the teacher model to train two student models: DPAL-BERT-Bi and DPAL-BERT-C. This research enhances the dataset More >

Abdulaziz Al-Besher¹, Kailash Kumar¹, M. Sangeetha^2,*, Tinashe Butsa³

CMC-Computers, Materials & Continua, Vol.70, No.3, pp. 4763-4780, 2022, DOI:10.32604/cmc.2022.021033 - 11 October 2021

Abstract Most of the questions from users lack the context needed to thoroughly understand the problem at hand, thus making the questions impossible to answer. Semantic Similarity Estimation is based on relating user’s questions to the context from previous Conversational Search Systems (CSS) to provide answers without requesting the user's context. It imposes constraints on the time needed to produce an answer for the user. The proposed model enables the use of contextual data associated with previous Conversational Searches (CS). While receiving a question in a new conversational search, the model determines the question that refers More >

Zhang Min, Teng Haibin, Jiang Ming, Wen Tao, Tang Jingfan

Intelligent Automation & Soft Computing, Vol.25, No.3, pp. 625-635, 2019, DOI:10.31209/2019.100000117

Abstract Mapping from sentence phrases to knowledge graph resources is an important step for applications such as search engines, automatic question answering systems based on acknowledge base and knowledge graphs. The existing solution maps a simple phrase to a knowledge graph resource strictly or approximately from the text. However, it is difficult to detect phrases and map the composite semantic resource. This paper proposes a longest matching resource mapping scheme to solve this problem, namely, to find the longest substring in a sentence that can match the knowledge base resource. Based on this scheme, we propose More >