22,249 Hits in 6.0 sec

A Guided Template-Based Question Answering System over Knowledge Graphs

Lukas Biermann, Sebastian Walter, Philipp Cimiano
2018 International Conference Knowledge Engineering and Knowledge Management  
For this, a template-based approach is used to generate all possible questions from a given RDF dataset using a number of templates.  ...  To remedy this, we present a new guided approach to QA that ensures that all questions that can be entered into the system also return a corresponding answer.  ...  This is accomplished by a template-based approach that matches basic graph patterns over the data and, using a lexicon, generates different variants of asking the same question.  ... 
dblp:conf/ekaw/BiermannWC18 fatcat:7fmtykwh65hfplz2ydxjvrq6wm

Question Answering over Knowledge Graphs

Sareh Aghaei Dinani
2021 International Web Rule Symposium  
A knowledge graph-based question answering system targets to leverage facts in knowledge graphs to answer natural language questions and assist users to access the meaningful and pertinent knowledge, without  ...  With the increasing maturity of large-scale knowledge graphs, question answering over knowledge graphs has become a crucial topic and attracted massive attention.  ...  QA over knowledge graph provides a way for artificial intelligence systems to incorporate knowledge graphs as a key ingredient to answer human questions, which can benefit a variety of applications, such  ... 
dblp:conf/ruleml/Dinani21 fatcat:nxuowfovifa4lbys33ynf57mty

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.  ...  Fundação para a Ciência e a Tecnologia. Grant Number: PD/BD/142877/2018.  ... 
doi:10.1049/sfw2.12028 fatcat:uuhsewdvsnal5hwua3lecfexqi

Question Answering over Knowledge Graphs with Neural Machine Translation and Entity Linking [article]

Daniel Diomedi, Aidan Hogan
2021 arXiv   pre-print
The goal of Question Answering over Knowledge Graphs (KGQA) is to find answers for natural language questions over a knowledge graph.  ...  We rather propose a KGQA approach that delegates the processing of entities to entity linking (EL) systems.  ...  A number of works have specifically addressed the task of Question Answering over Knowledge Graphs (KGQA) down through the years.  ... 
arXiv:2107.02865v1 fatcat:dlnrcpihhbacjcmvkoe6lk7fsi

Knowledge-Based Legal Document Assembly [article]

Marko Marković, Stevan Gostojić
2020 arXiv   pre-print
This knowledgebase has two components - the formal knowledge of legal norms represented as a rule-base and the tacit knowledge represented by a document template.  ...  This paper proposes a knowledge-based legal document assembly method that uses a machine-readable representation of knowledge of legal professionals.  ...  It uses configuration created in the previous phase to guide a user through a question answering process. A user is asked a series of questions.  ... 
arXiv:2009.06611v1 fatcat:voqdgqqle5ettd2sr3ldlpvhbi

Complex Knowledge Base Question Answering: A Survey [article]

Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen
2022 arXiv   pre-print
Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success.  ...  Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions.  ...  Among them, knowledge base question answering (KBQA) is a task that aims to answer natural language questions with KBs acting as its knowledge source.  ... 
arXiv:2108.06688v2 fatcat:frcdrrhbsncm3kprehnz563yfq

Question Answering over Knowledge Graphs via Structural Query Patterns [article]

Weiguo Zheng, Mei Zhang
2019 arXiv   pre-print
Searching the structured query over the knowledge graph can produce answers to the question.  ...  Finally, answers can be retrieved by executing the constructed query graph over the knowledge graph.  ...  In this paper, we focus on constructing query graphs for answering natural language questions over a knowledge graph.  ... 
arXiv:1910.09760v2 fatcat:oghjct4335grvnyuhhk4tovdxy

Question Answering System over Linked Data: A Detailed Survey

G. M. Rasiqul Islam Rasiq, Abdullah Al Sefat, Tanjila Hossain, Md. Israt-E-Hasan Munna, Jubayeath Jahan Jisha, Mohammad Moinul Hoque
2020 ABC Research Alert  
Here we will discuss the main obstacles for the QA system in processing the questions and a detailed survey of the existing systems.  ...  to our various questions.  ...  lot to finish our literature review based research work.  ... 
doi:10.18034/abcra.v8i1.449 fatcat:whgbzdj5vrfktfwci5akwamh2e

A State-transition Framework to Answer Complex Questions over Knowledge Base

Sen Hu, Lei Zou, Xinbo Zhang
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Although natural language question answering over knowledge graphs have been studied in the literature, existing methods have some limitations in answering complex questions.  ...  knowledge graph to find the answers to question N .  ...  by matching Q S over the knowledge graph G.  ... 
doi:10.18653/v1/d18-1234 dblp:conf/emnlp/Hu0Z18 fatcat:5o627rceufaejlcymchuu7mqwe

Automated Template Generation for Question Answering over Knowledge Graphs

Abdalghani Abujabal, Mohamed Yahya, Mirek Riedewald, Gerhard Weikum
2017 Proceedings of the 26th International Conference on World Wide Web - WWW '17  
Templates are an important asset for question answering over knowledge graphs, simplifying the semantic parsing of input utterances and generating structured queries for interpretable answers.  ...  This paper presents QUINT, a system that automatically learns utterance-query templates solely from user questions paired with their answers.  ...  Templates Figure 2 outlines our system for learning and subsequently using templates to answer natural language questions over knowledge graphs.  ... 
doi:10.1145/3038912.3052583 dblp:conf/www/AbujabalYRW17 fatcat:tot2vlwlbbda3lcaznk2fdazaa

COOKIE: A Dataset for Conversational Recommendation over Knowledge Graphs in E-commerce [article]

Zuohui Fu, Yikun Xian, Yaxin Zhu, Yongfeng Zhang, Gerard de Melo
2020 arXiv   pre-print
In this work, we present a new dataset for conversational recommendation over knowledge graphs in e-commerce platforms called COOKIE.  ...  Specifically, we first construct a unified knowledge graph and extract key entities between user--product pairs, which serve as the skeleton of a conversation.  ...  To this end, we present a novel corpus called COOKIE: COnversational recommendation Over Knowledge graphs In E-commerce platforms.  ... 
arXiv:2008.09237v1 fatcat:agnch5bxxjcebcswpy3mkbltte

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.  ...  Besides traditional methods relying on templates and rules, the research is categorized into a taxonomy that contains two main branches, namely Information Retrieval-based and Neural Semantic Parsing-based  ...  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


Wanyun Cui, Yanghua Xiao, Haixun Wang, Yangqiu Song, Seung-won Hwang, Wei Wang
2017 Proceedings of the VLDB Endowment  
Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases.  ...  In this paper, we design a new kind of question representation: templates, over a billion scale knowledge base and a million scale QA corpora.  ...  CONCLUSION QA over knowledge bases now becomes an important and feasible task. In this paper, we build a question answering system KBQA over a very large open domain RDF knowledge base.  ... 
doi:10.14778/3055540.3055549 fatcat:mtyi3kzcxvdp7otp5jrzqedqqq

Explanation as Question Answering based on Design Knowledge [article]

Ashok Goel, Vrinda Nandan, Eric Gregori, Sungeun An, Spencer Rugaber
2021 arXiv   pre-print
In this paper, we describe a question answering agent (AskJill) that uses the User Guide for an interactive learning environment (VERA) to automatically answer questions and thereby explains the domain  ...  However, few humans actually read the User Guide in detail. Instead, most users seek answers to their questions on demand.  ...  However, Jill Watson answered questions based on course materials such as class syllabi and schedule, by answering questions based on VERA's Users Guide, AskJill generalizes the approach.  ... 
arXiv:2112.09616v1 fatcat:vgcrtvol6za6zirajgntfded5e

Controllable Open-ended Question Generation with A New Question Type Ontology [article]

Shuyang Cao, Lu Wang
2021 arXiv   pre-print
We then propose a novel question type-aware question generation framework, augmented by a semantic graph representation, to jointly predict question focuses and produce the question.  ...  A new dataset with 4,959 questions is labeled based on the new ontology.  ...  Acknowledgements This research is supported in part by National Science Foundation through Grants IIS-1813341 and a CAREER award IIS-2046016.  ... 
arXiv:2107.00152v1 fatcat:54tyfwwrafdfphiee2m5he57xe
« Previous Showing results 1 — 15 out of 22,249 results