paper-with-me

Papers

Augmenting Neural Networks with First-order Logic

2019-06-14 · ACL 2019 7 · Tao Li, Vivek Srikumar

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.

📄 PDF Abstract BibTeX arXiv:1906.06298

Code (1)

utahnlp/layer_augmentation 공식 구현 pytorch

Tasks

ChunkingNatural Language InferenceOpen-Ended Question AnsweringReading ComprehensionWorld Knowledge

Similar Papers 제목 키워드 기반

Logical Negation Augmenting and Debiasing for Prompt-based Methods

2024-05-08 · Yitian Li, Jidong Tian, Hao He, Yaohui Jin

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 ReasoningNegation

Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding

2025-03-16 · Imran Kabir, Md Alimoor Reza, Syed Billah

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+2

Second-Order Word Embeddings from Nearest Neighbor Topological Features

2017-05-23 · Denis Newman-Griffis, Eric Fosler-Lussier

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+2

A Morphology-Based Investigation of Positional Encodings

2024-04-06 · Poulami Ghosh, Shikhar Vashishth, Raj Dabre, Pushpak Bhattacharyya

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+1

The inexact power augmented Lagrangian method for constrained nonconvex optimization

2024-10-26 · Alexander Bodard, Konstantinos Oikonomidis, Emanuel Laude, Panagiotis Patrinos

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…