您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference

文献类型： 会议论文

第一作者： Mokanarangan Thayaparan

作者： Mokanarangan Thayaparan 1 ; Marco Valentino 2 ; Andre Freitas 3 ;

作者机构： 1.Department of Computer Science, University of Manchester, UK##Idiap Research Institute, Switzerland

2.Idiap Research Institute, Switzerland

3.Department of Computer Science, University of Manchester, UK##National Biomarker Centre, CRUK-MI, University of Manchester, UK##Idiap Research Institute, Switzerland

关键词： Natural Language Inference;Neuro-Symbolic Al;Constrained Optimization

会议名称： Joint International Conference on Computational Linguistics, Language Resources and Evaluation

主办单位：

页码： 449-458

摘要： Integer Linear Programming (ILP) has been proposed as a formalism for encoding precise structural and semantic constraints for Natural Language Inference (NLI). However, traditional ILP frameworks are non-differentiable, posing critical challenges for the integration of continuous language representations based on deep learning. In this paper, we introduce a novel approach, named Diff-Comb Explainer, a neuro-symbolic architecture for explanation-based NLI based on Differentiable BlackBox Combinatorial Solvers (DBCS). Differently from existing neuro-symbolic solvers, Diff-Comb Explainer does not necessitate a continuous relaxation of the semantic constraints, enabling a direct, more precise, and efficient incorporation of neural representations into the ILP formulation. Our experiments demonstrate that Diff-Comb Explainer achieves superior performance when compared to conventional ILP solvers, neuro-symbolic black-box solvers, and Transformer-based encoders. Moreover, a deeper analysis reveals that Diff-Comb Explainer can significantly improve the precision, consistency, and faithfulness of the constructed explanations, opening new opportunities for research on neuro-symbolic architectures for explainable and transparent NLI in complex domains.

分类号： tp31

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台