Modeling Content and Context with Deep Relational Learning
TLDR
DRaiL is presented, an open-source declarative framework for specifying deep relational models, designed to support a variety of NLP scenarios, and provides an interface to study the interactions between representation, inference and learning.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.read more
Citations
More filters
Rethinking Context Language As An Interactive Phenomenon
TL;DR: Thank you very much for reading rethinking context language as an interactive phenomenon, and maybe you have knowledge that, people have search hundreds of times for their chosen readings, but end up in harmful downloads.
Proceedings ArticleDOI
Analysis of Nuanced Stances and Sentiment Towards Entities of US Politicians through the Lens of Moral Foundation Theory.
Shamik Roy,Dan Goldwasser +1 more
TL;DR: The Moral Foundation Theory is studied in tweets by US politicians on two politically divisive issues - Gun Control and Immigration to show there is a strong correlation between the moral foundation usage and the politicians’ nuanced stance on a particular topic.
Journal ArticleDOI
Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
TL;DR: A structured review of studies implementing NeSy for NLP is conducted, with the aim of answering the question of whether NeSy is indeed meeting its promises: reasoning, out-of-distribution generalization, interpretability, learning and reasoning from small data, and transferability to new domains.
Proceedings ArticleDOI
A Holistic Framework for Analyzing the COVID-19 Vaccine Debate
Maria Leonor Pacheco,Tunazzina Islam,Monal Mahajan,Andrey Shor,Ming Yin,Lyle H. Ungar,Dan Goldwasser +6 more
TL;DR: This work proposes a holistic analysis framework connecting stance and reason analysis, and fine-grained entity level moral sentiment analysis and shows that this framework provides reliable predictions even in the low-supervision settings.
Proceedings ArticleDOI
Tackling Fake News Detection by Continually Improving Social Context Representations using Graph Neural Networks
TL;DR: Inference operators are formulated which augment the graph edges by revealing unobserved interactions between its elements, such as similarity between documents’ contents and users’ engagement patterns, resulting in improved performance in fake news detection experiments.
References
More filters
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Proceedings ArticleDOI
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Journal ArticleDOI
Birds of a Feather: Homophily in Social Networks
TL;DR: The homophily principle as mentioned in this paper states that similarity breeds connection, and that people's personal networks are homogeneous with regard to many sociodemographic, behavioral, and intrapersonal characteristics.
Posted Content
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
TL;DR: A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
Proceedings ArticleDOI
DeepWalk: online learning of social representations
TL;DR: DeepWalk as mentioned in this paper uses local information obtained from truncated random walks to learn latent representations by treating walks as the equivalent of sentences, which encode social relations in a continuous vector space, which is easily exploited by statistical models.