Modeling Content and Context with Deep Relational Learning
Open Access
- 1 February 2021
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 9, 100-119
Abstract
Building models for realistic natural language tasks requires dealing with long texts and accounting for complicated structural dependencies. Neural-symbolic representations have emerged as a way to combine the reasoning capabilities of symbolic methods, with the expressiveness of neural networks. However, most of the existing frameworks for combining neural and symbolic representations have been designed for classic relational learning tasks that work over a universe of symbolic entities and relations. In this paper, we present DRaiL, an open-source declarative framework for specifying deep relational models, designed to support a variety of NLP scenarios. Our framework supports easy integration with expressive language encoders, and provides an interface to study the interactions between representation, inference and learning.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Parsing Argumentation Structures in Persuasive EssaysComputational Linguistics, 2017
- Globally Normalized Transition-Based Neural Networks2016
- A large annotated corpus for learning natural language inference2015
- DeepWalk2014
- Probabilistic Soft Logic for Semantic Textual Similarity2014
- A Fast and Accurate Dependency Parser using Neural Networks2014
- Glove: Global Vectors for Word Representation2014
- Markov logic networksMachine Learning, 2006
- Birds of a Feather: Homophily in Social NetworksAnnual Review of Sociology, 2001
- Contextualization Revisited1992