Compositional Language Understanding with Text-based Relational Reasoning
Neural networks for natural language reasoning have largely focused on extractive, fact-based question-answering (QA) and common-sense inference. However, it is also crucial to understand the extent to which neural networks can perform relational reasoning and combinatorial generalization from natural language---abilities that are often obscured by annotation artifacts and the dominance of language modeling in standard QA benchmarks. In this work, we present a novel benchmark dataset for language understanding that isolates performance on relational reasoning. We also present a neural message-passing baseline and show that this model, which incorporates a relational inductive bias, is superior at combinatorial generalization compared to a traditional recurrent neural network approach.
Code (2)
Tasks
Common Sense ReasoningInductive BiasLanguage ModelingLanguage ModellingQuestion AnsweringRelational ReasoningSimilar Papers 제목 키워드 기반
Inference-Time Structural Reasoning for Compositional Vision-Language Understanding
Vision-language models (VLMs) excel at image-text retrieval yet persistently fail at compositional reasoning, distinguishing captions that share the same words but differ in relational structure. We present, a unified ev…
Text RetrievalLeveraging Textual Compositional Reasoning for Robust Change Captioning
Change captioning aims to describe changes between a pair of images. However, existing works rely on visual features alone, which often fail to capture subtle but meaningful changes because they lack the ability to repre…
Relational ReasoningHyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning
Vision-Language Models (VLMs) struggle with compositional reasoning that requires understanding inter-object relationships. A natural remedy is to inject explicit scene graph triplets $\langle s, p, o \rangle$ from an of…
Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray
Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray baggage screening, however, threat often emerges not from a single object…
Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-language models (VLMs) offer promising semantic flexibility, they lack …
Scene UnderstandingAutonomous DrivingVisual Reasoning