arXiv：cs.CL· Xuyao Feng, Antonis Bikakis·· 16 小时前
从句子级监督学习命题级链接，用于神经符号 NLI
Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI
AI 导读
研究者提出一种可训练的 atom linker，联合预测命题单元间的链接存在性、来源选择与关系类型，在无 atom 对标注的情况下，将跨公式链接结构视为隐变量，仅用句子级 NLI 标签训练，翻译器与 SAT 推理器保持固定。
正文
Abstract:We study neuro-symbolic natural language inference (NLI) with independently translated propositional representations of the premise and hypothesis. Before symbolic reasoning, the system must infer semantic links between their proposition-level units (atoms). Existing systems based on Abstract Meaning Representation (AMR) and Boolean satisfiability (SAT) identify these links using fixed embedding-based source selection and pretrained sentence-level NLI models not trained for atom-level linking. We introduce a trainable atom linker that jointly predicts link existence, source selection, and relation type. Without atom-pair training annotations, we treat cross-formula link structures as latent and train the linker from sentence-level NLI labels, keeping the translator and SAT reasoner fixed. We evaluate on the full public test splits of Stanford Natural Language Inference (SNLI) and Sentences Involving Compositional Knowledge (SICK), and the matched and mismatched validation splits of Multi-Genre Natural Language Inference (MNLI). Our system improves accuracy by 11.40-27.09 percentage points over a baseline applying sentence-trained NLI models unchanged to atom pairs within the same SAT pipeline. It also improves over the prior fixed-linker AMR-to-SAT system by 8.14-26.32 percentage points on SNLI and both MNLI splits, with a smaller gain on SICK.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.15158 [cs.CL] |
| (or arXiv:2610.15158v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15158 arXiv-issued DOI via DataCite |
Submission history
From: Xuyao Feng [view email]
[v1]
Sat, 10 Oct 2026 20:16:23 UTC (60 KB)
[v2]
Wed, 14 Oct 2026 07:38:08 UTC (61 KB)
来源：arXiv：cs.CL · arxiv.org