Augmenting Neural Networks with First-order Logic
Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this paper, we present a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction. Our framework systematically compiles logical statements into computation graphs that augment a neural network without extra learnable parameters or manual redesign. We evaluate our modeling strategy on three tasks: machine comprehension, natural language inference, and text chunking. Our experiments show that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes.
Code (1)
Tasks
ChunkingNatural Language InferenceOpen-Ended Question AnsweringReading ComprehensionWorld KnowledgeSimilar Papers 제목 키워드 기반
Logical Negation Augmenting and Debiasing for Prompt-based Methods
Prompt-based methods have gained increasing attention on NLP and shown validity on many downstream tasks. Many works have focused on mining these methods' potential for knowledge extraction, but few explore their ability…
Logical ReasoningNegationLogic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding
Large multimodal models (LMMs) are increasingly integrated into autonomous driving systems for user interaction. However, their limitations in fine-grained spatial reasoning pose challenges for system interpretability an…
Autonomous DrivingRAGRetrieval-augmented Generationroad scene understanding+2Second-Order Word Embeddings from Nearest Neighbor Topological Features
We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Natural Language Inference+2A Morphology-Based Investigation of Positional Encodings
Contemporary deep learning models effectively handle languages with diverse morphology despite not being directly integrated into them. Morphology and word order are closely linked, with the latter incorporated into tran…
Dependency Parsingnamed-entity-recognitionNamed Entity RecognitionNatural Language Inference+1The inexact power augmented Lagrangian method for constrained nonconvex optimization
This work introduces an unconventional inexact augmented Lagrangian method, where the augmenting term is a Euclidean norm raised to a power between one and two. The proposed algorithm is applicable to a broad class of co…