Natural Language Inference by Tree-Based Convolution and Heuristic Matching

Lili Mou, Rui Men, Ge Li, Yan Xu, Lu Zhang, Rui Yan, Zhi Jin

2015-12-28ACL 2016 8Natural Language Inference

Abstract

In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heuristic matching layers like concatenation, element-wise product/difference combine the information in individual sentences. Experimental results show that our model outperforms existing sentence encoding-based approaches by a large margin.

Results

Task	Dataset	Metric	Value	Model
Natural Language Inference	SNLI	% Test Accuracy	82.1	300D Tree-based CNN encoders
Natural Language Inference	SNLI	% Train Accuracy	83.3	300D Tree-based CNN encoders

Related Papers

LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification2025-07-15 DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification2025-07-08 ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation2025-06-27 Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding2025-06-17 When Does Meaning Backfire? Investigating the Role of AMRs in NLI2025-06-17 Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure2025-06-10 Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models2025-06-08 A MISMATCHED Benchmark for Scientific Natural Language Inference2025-06-05