Bridging Knowledge Gaps in Neural Entailment via Symbolic Models
Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural Language InferenceSimilar Papers 제목 키워드 기반
Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment
This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using contextual embeddings (e.g., Sentence-B…
Knowledge GraphsEnhancing Systematic Decompositional Natural Language Inference Using Informal Logic
Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on brittle formal logic. However, progress in…
Formal LogicKnowledge DistillationNatural Language InferencevalidCan Pre-trained Models Really Generate Single-Step Textual Entailment?
We investigate the task of generating textual entailment (GTE). Different from prior works on recognizing textual entailment, also known as NLI, GTE requires the models with deeper reasoning capabilities - generating ent…
Natural Language InferenceRTEvalidMINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation
Joint planning through language-based interactions is a key area of human-AI teaming. Planning problems in the open world often involve various aspects of incomplete information and unknowns, e.g., objects involved, huma…
Embedding Symbolic Knowledge into Deep Networks
In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augm…
Graph EmbeddingRelation PredictionRepresentation Learning