Representation Learning of Logical Query for Knowledge Reasoning

Wang, Yashen; Zhang, Huanhuan; Liu, Yifeng

doi:10.1109/icsidp47821.2019.9173125

Cited by 117 publications

(225 citation statements)

References 22 publications

Supporting

Mentioning

225

Contrasting

Order By: Relevance

“…TensorLog is (Cohen et al 2017) a recently developed differentiable logic that performs approximate first‐order logic inference through a sequence of differentiable numerical operations on matrices. NeuralLP (F. Yang et al, 2017), inspired by TensorLog, learns to map an input question to its answer by performing multi‐step knowledge base reasoning by means of differentiable graph traversal operations.…”

Section: Neural Network‐based Kgqa Systemsmentioning

confidence: 99%

“…Question answering over knowledge graphs has been an important area of research in the past decade. Them being the use of query graph candidates (Maheshwari et al, 2019; Yih et al, 2015; M. Yu et al, 2017), the use of neural symbolic machines (C. Liang et al, 2017), the shift to answering multi‐entity questions (Luo et al, 2018), the application of transfer learning (Maheshwari et al, 2019), and the proposal of differentiable query execution‐based weakly supervised models (F. Yang et al, 2017). Petrochuk and Zettlemoyer (2018) suggest that the performance on SimpleQuestions is approaching an upper bound.…”

Section: Emerging Trendsmentioning

confidence: 99%

“…More recently, increasingly many neural network‐based approaches have been shown to be effective for the KGQA task as well. These approaches employ neural architectures ranging from simple neural embedding‐based models (Bordes, Chopra, & Weston, 2014), over attention‐based recurrent models (Cheng, Reddy, Saraswat, & Lapata, 2019), to memory‐augmented neural controller architectures (C. Liang, Berant, Le, Forbus, & Lao, 2017; Neelakantan, Le, Abadi, McCallum, & Amodei, 2017; F. Yang, Z. Yang, & Cohen, 2017).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Introduction to neural network‐based question answering over knowledge graphs

Chakraborty

Lukovnikov²,

Maheshwari

et al. 2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Question answering has emerged as an intuitive way of querying structured data sources and has attracted significant advancements over the years. A large body of recent work on question answering over knowledge graphs (KGQA) employs neural network‐based systems. In this article, we provide an overview of these neural network‐based methods for KGQA. We introduce readers to the formalism and the challenges of the task, different paradigms and approaches, discuss notable advancements, and outline the emerging trends in the field. Through this article, we aim to provide newcomers to the field with a suitable entry point to semantic parsing for KGQA, and ease their process of making informed decisions while creating their own QA systems. This article is categorized under: Technologies > Machine Learning Technologies > Prediction Technologies > Artificial Intelligence

show abstract

Section: Neural Network‐based Kgqa Systemsmentioning

confidence: 99%

Section: Emerging Trendsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Introduction to neural network‐based question answering over knowledge graphs

Chakraborty

Lukovnikov²,

Maheshwari

et al. 2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…These systems are designed for inducing rules from symbolic knowledge bases, which is not in the scope of our framework. In this space we find Neural Theorem Provers (NTPs) (Rocktäschel and Riedel, 2017), Neural Logic Programming (Yang et al, 2017), DRUM (Sadeghian et al, 2019) and Neural Logic Machines (NLMs) (Dong et al, 2019). NTPs use a declarative interface to specify rules that add inductive bias and perform soft proofs.…”

Section: Hybrid Neural-symbolic Approachesmentioning

confidence: 99%

Modeling Content and Context with Deep Relational Learning

Pacheco

Goldwasser

2021

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

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.

show abstract

“…Neuro-symbolic AI employs neural networks for rule induction (Yang et al, 2017;Evans and Grefenstette, 2018;Dong et al, 2019). To the best of our knowledge however, none of these address NLP tasks such as sentence classification.…”

Section: Related Workmentioning

confidence: 99%

Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification

Sen¹,

Danilevsky²,

Li³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Interpretability of predictive models is becoming increasingly important with growing adoption in the real-world. We present RuleNN, a neural network architecture for learning transparent models for sentence classification. The models are in the form of rules expressed in first-order logic, a dialect with well-defined, human-understandable semantics. More precisely, RuleNN learns linguistic expressions (LE) built on top of predicates extracted using shallow natural language understanding. Our experimental results show that RuleNN outperforms statistical relational learning and other neuro-symbolic methods, and performs comparably with black-box recurrent neural networks. Our user studies confirm that the learned LEs are explainable and capture domain semantics. Moreover, allowing domain experts to modify LEs and instill more domain knowledge leads to human-machine cocreation of models with better performance.

show abstract

Representation Learning of Logical Query for Knowledge Reasoning

Cited by 117 publications

References 22 publications

Introduction to neural network‐based question answering over knowledge graphs

Introduction to neural network‐based question answering over knowledge graphs

Modeling Content and Context with Deep Relational Learning

Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification

Contact Info

Product

Resources

About