Filters








32,354 Hits in 4.7 sec

Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network [article]

Deming Ye, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Maosong Sun
2019 arXiv   pre-print
In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs reasoning over multiple paragraphs with entities.  ...  To explicitly capture the entities' relatedness, KGNN utilizes relational facts in knowledge graph to build the entity graph.  ...  introduce entity graph neural network to reason over entities for Knowledge Base QA (KBQA).  ... 
arXiv:1911.02170v1 fatcat:2fzzx7vjxjhbviy2twmhj7l7xa

Visual Experience-Based Question Answering with Complex Multimodal Environments

Incheol Kim, Jiayi Ma
2020 Mathematical Problems in Engineering  
To address this VEQA problem, we propose a hybrid visual question answering system, VQAS, integrating a deep neural network-based scene graph generation model and a rule-based knowledge reasoning system  ...  Moreover, it can answer complex questions through knowledge reasoning with rich background knowledge.  ...  Different from the pure deep neural network-based models, the proposed knowledge reasoning system can use a rich knowledge source to answer questions by combining the shallow knowledge in 3D scene graphs  ... 
doi:10.1155/2020/8567271 fatcat:cgmzylh4ujadfisikt5hekvrga

Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction [article]

Xinmeng Li, Mamoun Alazab, Qian Li, Keping Yu, Quanjun Yin
2021 arXiv   pre-print
Knowledge graph question answering is an important technology in intelligent human-robot interaction, which aims at automatically giving answer to human natural language question with the given knowledge  ...  To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process.  ...  Figure 1 : 1 An example of multi-relation question over knowledge graph from World-Cup2014 Figure 2 : 2 The architecture of memory neural network and key-value memory neural network.  ... 
arXiv:2104.13173v1 fatcat:3v43jnf74rfyzi2x54df7vpk5i

RelNet: End-to-End Modeling of Entities & Relations [article]

Trapit Bansal, Arvind Neelakantan, Andrew McCallum
2017 arXiv   pre-print
The model thus builds an abstract knowledge graph on the entities and relations present in a document which can then be used to answer questions about the document.  ...  It is trained end-to-end: only supervision to the model is in the form of correct answers to the questions.  ...  Often such problems are formulated as reasoning over graph-structured representation of knowledge.  ... 
arXiv:1706.07179v2 fatcat:gv4tx6ecdja2fiem6fztl25oau

Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks [article]

Salman Mohammed, Peng Shi, Jimmy Lin
2018 arXiv   pre-print
We examine the problem of question answering over knowledge graphs, focusing on simple questions that can be answered by the lookup of a single fact.  ...  On the popular SimpleQuestions dataset, we find that basic LSTMs and GRUs plus a few heuristics yield accuracies that approach the state of the art, and techniques that do not use neural networks also  ...  Introduction There has been significant recent interest in simple question answering over knowledge graphs, where a natural language question such as "Where was Sasha Vujacic born?"  ... 
arXiv:1712.01969v2 fatcat:frf4chbaxndyfeq65eumyp5wy4

Systematic review of question answering over knowledge bases

Arnaldo Pereira, Alina Trifan, Rui Pedro Lopes, José Luís Oliveira
2021 IET Software  
Because question answering over knowledge bases (KBQAs) is a very active research topic, a comprehensive view of the field is essential.  ...  Several proposals to overcome this difficulty have suggested using question answering (QA) systems to provide user-friendly interfaces and allow natural language use.  ...  knowledge graphs Info. extraction 2017 35 Neural network-based question answering over knowledge graphs on word and character levels [9] Info. extraction 2017 36 QAESTRO-semantic-based composition  ... 
doi:10.1049/sfw2.12028 fatcat:uuhsewdvsnal5hwua3lecfexqi

A Survey of Knowledge Reasoning based on KG

Rui Lu, Zhiping Cai, Shan Zhao
2019 IOP Conference Series: Materials Science and Engineering  
This article presents a brief overview of KR based on KG, expounds the connotation and research scope of it, judges the two main research directions(Knowledge Graph Completion(KGC) and Question Answering  ...  KR based on Knowledge Graph(KG) is based on existing KG's facts.  ...  Question Answering over Knowledge Graph (QA-KG) Question Answering over Knowledge Graph (QA-KG) [14] aims to use facts in the KG to answer natural language questions.  ... 
doi:10.1088/1757-899x/569/5/052058 fatcat:erpnnqzsy5hmhbgidjsb7dmplu

Visual Question Answering: A Survey of Methods and Datasets [article]

Qi Wu, Damien Teney, Peng Wang, Chunhua Shen, Anthony Dick, Anton van den Hengel
2016 arXiv   pre-print
Given an image and a question in natural language, it requires reasoning over visual elements of the image and general knowledge to infer the correct answer.  ...  In particular, we examine the common approach of combining convolutional and recurrent neural networks to map images and questions to a common feature space.  ...  Acknowledgements This research was in part supported by the Data to Decisions Cooperative Research Centre funded by the Australian Government.  ... 
arXiv:1607.05910v1 fatcat:ijh4zruldjhwxpbuwulpyogsxy

Neural Relation Prediction for Simple Question Answering over Knowledge Graph [article]

Amin Abolghasemi, Saeedeh Momtazi
2020 arXiv   pre-print
Knowledge graphs are widely used as a typical resource to provide answers to factoid questions.  ...  In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of predefined relation types.  ...  Results As mentioned, our instance-based idea for question answering over knowledge graph requires a text matching model to find similar question to the input question.  ... 
arXiv:2002.07715v3 fatcat:an3pjyzxsfb4raijxayhyfdj74

Helping the ineloquent farmers: Finding experts for questions with limited text in agricultural Q&A Communities

Xiaoxue Shen, Adele Lu Jia, Siqi Shen, Yong Dou
2020 IEEE Access  
We propose a novel approach based on graph neural network to accurately recommend for each question the users that are highly likely to answer it.  ...  INDEX TERMS Question and answering, question routing, network representation learning.  ...  INTRODUCTION Community-based Question and Answering (CQA) systems have become popular knowledge-sharing platforms where users get answers to the questions they raised.  ... 
doi:10.1109/access.2020.2984342 fatcat:z3h3nkswyzeudid6r77n23nlx4

Relational Graph Representation Learning for Open-Domain Question Answering [article]

Salvatore Vivona, Kaveh Hassani
2019 arXiv   pre-print
We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task.  ...  Our model can learn contextual representation by jointly learning and updating the query, knowledge graph, and document representations.  ...  Introduction Fusing structured knowledge from knowledge graphs into deep models using Graph Neural Networks (GNN) [23, 30, 29] is shown to improve their performance on tasks such as visual question answering  ... 
arXiv:1910.08249v1 fatcat:hboox75tynahrdfin7pdr4dofa

Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph [article]

Hanning Gao, Lingfei Wu, Po Hu, Zhihua Wei, Fangli Xu, Bo Long
2021 arXiv   pre-print
Knowledge graph question answering (i.e., KGQA) based on information retrieval aims to answer a question by retrieving answer from a large-scale knowledge graph.  ...  Our proposed model combines a novel subgraph matching networks to capture global interactions in both question and subgraphs and an Enhanced Bilateral Multi-Perspective Matching model to capture local  ...  INTRODUCTION With the rise of large-scale knowledge graphs (KG) such as DBpedia [2] and Freebase [7] , question answering over knowledge graph (KGQA) has attracted massive attention recently, which  ... 
arXiv:2111.10541v1 fatcat:bnymdms63rcevdvnlsupexqcje

Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks

Salman Mohammed, Peng Shi, Jimmy Lin
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)  
We examine the problem of question answering over knowledge graphs, focusing on simple questions that can be answered by the lookup of a single fact.  ...  On the popular SIMPLEQUESTIONS dataset, we find that basic LSTMs and GRUs plus a few heuristics yield accuracies that approach the state of the art, and techniques that do not use neural networks also  ...  Introduction There has been significant recent interest in simple question answering over knowledge graphs, where a natural language question such as "Where was Sasha Vujacic born?"  ... 
doi:10.18653/v1/n18-2047 dblp:conf/naacl/MohammedSL18 fatcat:xth4brhm2fhgvpr4kw5gz373zq

Tackling Graphical Natural Language Processing's Problems with Recurrent Neural Networks

Ali Sami Sosa, Saja Majeed Mohammed, Haider Hadi Abbas, Israa Al Barazanchi
2019 Journal of Southwest Jiaotong University  
problems, including machine translation and question answering.  ...  Despite these successes, recurrent neural network -based models continue to suffer from several major drawbacks.  ...  These graphs include semantic graphs, dependency graphs, and knowledge graphs used by recurrent neural networks.  ... 
doi:10.35741/issn.0258-2724.54.5.35 fatcat:6vimnp7scrahhbfl2cdmwa3q5u

A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges [article]

Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun
2020 arXiv   pre-print
Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases.  ...  In order to make KBQA more applicable in actual scenarios, researchers have shifted their attention from simple questions to complex questions, which require more KB triples and constraint inference.  ...  Background Question Answering (QA) over Knowledge Base (KB) uses rich semantic information to deeply understand natural language questions and provide answers from knowledge bases.  ... 
arXiv:2007.13069v1 fatcat:os3d7isfubfjlmvstrazpw7mra
« Previous Showing results 1 — 15 out of 32,354 results