Natural Language Inference Using Evidence from Knowledge Graphs

查看全文 作　　者：Boxuan [1]Jia;Hui [1]Xu;Maosheng [2]Guo 机构地区：[1]School of Computer Science and Technology,Heilongjiang University,Harbin,China;[2]Harbin Institute of Technology,Harbin,China 出　　处：《国际计算机前沿大会会议论文集》索引2021年第2期,共13页 基　　金：This work is supported by Basic Research Funds for Higher Education Institution in Heilongjiang Province(Fundamental Research Project,Grant No.2020-KYYWF-1011). 摘　　要：Knowledge plays an essential role in inference,but is less explored by previous works in the Natural Language Inference(NLI)task.Although traditional neural models obtained impressive performance on standard benchmarks,they often encounter performance degradation when being applied to knowledge-intensive domains like medicine and science.To address this problem and further fill the knowledge gap,we present a simple Evidence-Based Inference Model(EBIM)to integrate clues collected from knowledge graphs as evidence for inference.To effectively incorporate the knowledge,we propose an efficient approach to retrieve paths in knowledge graphs as clues and then prune them to avoid involving too much irrelevant noise.In addition,we design a specialized CNN-based encoder according to the structure of clues to better model them.Experiments show that the proposed encoder outperforms strong baselines,and our EBIM model outperforms other knowledge-based approaches on the SciTail benchmark and establishes a new state-of-the-art performance on the MedNLI dataset. 关 键 词：Knowledge graphs Natural language processing Natural Language Inference Neural networks