Papers Systematic Generalization
“Systematic Generalization” 태그가 달린 논문 126편 · 필터 해제
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text
The recent success of natural language understanding (NLU) systems has been troubled by results highlighting the failure of these models to generalize in a systematic and robust way. In this work, we introduce a diagnost…
DiagnosticGraph Neural NetworkInductive logic programmingNatural Language Understanding+2A Perspective on Objects and Systematic Generalization in Model-Based RL
In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledg…
Systematic GeneralizationCompositional generalization in a deep seq2seq model by separating syntax and semantics
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, hum…
Deep LearningMachine TranslationSystematic GeneralizationTranslationLinguistic generalization and compositionality in modern artificial neural networks
In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess effective generalizat…
Systematic GeneralizationMulti-Object Representation Learning with Iterative Variational Inference
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning w…
ObjectRepresentation LearningSystematic GeneralizationUnsupervised Object Segmentation+1Systematic Generalization: What Is Required and Can It Be Learned?
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appealing modular models that require backgr…
Systematic GeneralizationVisual Question Answering (VQA)