Filters








424 Hits in 3.0 sec

Evaluating Question Answering Over Linked Data

Vanessa Lopez, Christina Unger, Philipp Cimiano, Enrico Motta
2013 Social Science Research Network  
To address this gap, we have set up a series of evaluation challenges for question answering over linked data.  ...  In recent years, there have been important advances in semantic search and question answering over RDF data.  ...  In this paper we describe public evaluation challenges for question answering systems over linked data: QALD.  ... 
doi:10.2139/ssrn.3199070 fatcat:5ozki3gprnb4tdhcbt5srwiqrm

Evaluating question answering over linked data

Vanessa Lopez, Christina Unger, Philipp Cimiano, Enrico Motta
2013 Journal of Web Semantics  
To address this gap, we have set up a series of evaluation challenges for question answering over linked data.  ...  In recent years, there have been important advances in semantic search and question answering over RDF data.  ...  In this paper we describe public evaluation challenges for question answering systems over linked data: QALD.  ... 
doi:10.1016/j.websem.2013.05.006 fatcat:pm6ivyx5dzaphauenqfhcjnmnm

Where is Linked Data in Question Answering over Linked Data? [article]

Tommaso Soru, Edgard Marx, André Valdestilhas, Diego Moussallem, Gustavo Publio, Muhammad Saleem
2020 arXiv   pre-print
We argue that "Question Answering with Knowledge Base" and "Question Answering over Linked Data" are currently two instances of the same problem, despite one explicitly declares to deal with Linked Data  ...  We point out the lack of existing methods to evaluate question answering on datasets which exploit external links to the rest of the cloud or share common schema.  ...  Hence the question in the title, "Where is Linked Data in Question Answering over Linked Data"?  ... 
arXiv:2005.03640v1 fatcat:i7gxlwcrlbadxetjdjkmtzaltq

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data [article]

Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
2018 arXiv   pre-print
The task of answering natural language questions over RDF data has received wide interest in recent years, in particular in the context of the series of QALD benchmarks.  ...  We present the first multilingual QALD pipeline that induces a model from training data for mapping a natural language question into logical form as probabilistic inference.  ...  We have applied our approach to the task of question answering over linked data, using the QALD-6 dataset.  ... 
arXiv:1802.09296v1 fatcat:e4oc3eadpnbkfifq4wu2kptcgq

Question Answering over Linked Data Using First-order Logic

Shizhu He, Kang Liu, Yuanzhe Zhang, Liheng Xu, Jun Zhao
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
Question Answering over Linked Data (QALD) aims to evaluate a question answering system over structured data, the key objective of which is to translate questions posed using natural language into structured  ...  In this way, our method can cover more text expressions and answer more questions than previous methods using manually designed patterns.  ...  answering over linked data using a Markov Logic Network (MLN).  ... 
doi:10.3115/v1/d14-1116 dblp:conf/emnlp/HeLZX014 fatcat:ku5k5ks5dfc5pjxh2zfbbjfzry

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  
to our various questions.  ...  We also discuss the evaluation campaigns of the existing models based on their precision, recall and F-1 scores on the QALD dataset.  ...  Answering system over Linked Data.  ... 
doi:10.18034/abcra.v8i1.449 fatcat:whgbzdj5vrfktfwci5akwamh2e

Robust question answering over the web of linked data

Mohamed Yahya, Klaus Berberich, Shady Elbassuoni, Gerhard Weikum
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Knowledge bases and the Web of Linked Data have become important assets for search, recommendation, and analytics.  ...  However, question answering technology does not work robustly in this setting as questions have to be translated into structured queries and users have to be careful in phrasing their questions.  ...  Benchmark: As our main test case, we adopted the benchmark from the 2nd Workshop on Question Answering over Linked Data [35] .  ... 
doi:10.1145/2505515.2505677 dblp:conf/cikm/YahyaBEW13 fatcat:o7qklxaarvbqjcgjjxkprkzxfi

Multilingual Question Answering over Linked Data (QALD-3): Lab Overview [chapter]

Philipp Cimiano, Vanessa Lopez, Christina Unger, Elena Cabrio, Axel-Cyrille Ngonga Ngomo, Sebastian Walter
2013 Lecture Notes in Computer Science  
The third instalment of the open challenge on Question Answering over Linked Data (QALD-3) has been conducted as a half-day lab at CLEF 2013.  ...  Differently from previous editions of the challenge, QALD-3 put a strong emphasis on multilinguality, offering two tasks: one on multilingual question answering and one on ontology lexicalization.  ...  The first edition, QALD-1, was organised in the context of the workshop Question Answering Over Linked Data at ESWC 2011.  ... 
doi:10.1007/978-3-642-40802-1_30 fatcat:glwebrqehrae7ksid6lvfvkmoe

An Introduction to Question Answering over Linked Data [chapter]

Christina Unger, André Freitas, Philipp Cimiano
2014 Lecture Notes in Computer Science  
This tutorial gives an introduction to the rapidly developing eld of question answering over linked data.  ...  Finally, it lists the open topics that will keep question answering over linked data an exciting area of research in the years to come. 1  ...  In Section 5 we then list tools and resources that proved useful for question answering over linked data and that can get you started in building your own system.  ... 
doi:10.1007/978-3-319-10587-1_2 fatcat:nhztb5gl2zdxlp53xkp2ndsasq

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data [chapter]

Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
2017 Lecture Notes in Computer Science  
The task of answering natural language questions over RDF data has received wIde interest in recent years, in particular in the context of the series of QALD benchmarks.  ...  We present the first multilingual QALD pipeline that induces a model from training data for mapping a natural language question into logical form as probabilistic inference.  ...  We have applied our approach to the task of question answering over linked data, using the QALD-6 dataset.  ... 
doi:10.1007/978-3-319-68288-4_20 fatcat:y7bkqxj64zen7p656jkhmhrs5m

7th Open Challenge on Question Answering over Linked Data (QALD-7) [chapter]

Ricardo Usbeck, Axel-Cyrille Ngonga Ngomo, Bastian Haarmann, Anastasia Krithara, Michael Röder, Giulio Napolitano
2017 Communications in Computer and Information Science  
QALD 1 has a 6-year history of developing a benchmark that is increasingly being used as standard evaluation tool for question answering over Linked Data.  ...  As training data, we included 105 questions in English from past challenges (partly based on questions used in the INEX Linked Data track 5 ).  ... 
doi:10.1007/978-3-319-69146-6_6 fatcat:625ecuwkajactklg26xroa7qfi

Generating Grammars from lemon lexica for Questions Answering over Linked Data: a Preliminary Analysis

Viktoria Benz, Mohammad Fazleh Elahi, Basil Ell, Philipp Cimiano
2020 Zenodo  
Most approaches to question answering over linked data (QALD) frame the task as a machine learning problem, consisting in learning a mapping from natural language questions into SPARQL queries by parametrizing  ...  We show that with a hand-crafted lexicon, we can in principle get very high micro-F1 scores of 62.5% on the training data of QALD-7 when questions are manually rephrased to fit our grammar.  ...  Introduction Most approaches to question answering over linked data (QALD) follow a machine learning (ML) approach where a QA system is learned by parametrizing a model on the basis of training data given  ... 
doi:10.5281/zenodo.6641630 fatcat:27n5ieql5zfndciv44wzyepzgq

6th Open Challenge on Question Answering over Linked Data (QALD-6) [chapter]

Christina Unger, Axel-Cyrille Ngonga Ngomo, Elena Cabrio
2016 Communications in Computer and Information Science  
The main objective of the open challenge on question answering over linked data 6 [2] (QALD) is to provide up-to-date, demanding benchmarks that establish a standard against which question answering  ...  QALD-5 is the fifth instalment of the QALD open challenge and focuses on multilingual and hybrid question answering as part of the Question Answering Lab 7 at CLEF 2015.  ... 
doi:10.1007/978-3-319-46565-4_13 fatcat:as3rmfpq3zcjde2mkmeo24x26a

A Study of URI Spotting for Question Answering over Linked Data (QALD) [chapter]

KyungTae Lim, NamKyoo Kang, Min-Woo Park
2016 IFIP Advances in Information and Communication Technology  
URI Spotting for QALD URI spotting refers to a process of finding the resources of the associated linked data from queries.  ...  In question answering systems such as QALD [1, 2, 3] , answer to the queries is found from DBpedia which is updated on a regular basis.  ... 
doi:10.1007/978-3-319-48390-0_17 fatcat:6vtz6lqp3ndqxcahu5oavpgf2i

Question answering over biomedical linked data with Grammatical Framework

Anca Marginean, Christina Unger, Axel-Cyrille Ngonga Ngomo, Philipp Cimiano, Sören Auer, George Paliouras, Christina Unger, Axel-Cyrille Ngonga Ngomo, Philipp Cimiano, Sören Auer, George Paliouras
2017 Semantic Web Journal  
The blending of linked data with ontologies leverages the access to data.  ...  Problems and solutions for querying biomedical linked data with Romanian, besides English, are also considered in the context of GF.  ...  These three sets were proposed in Task 2, Biomedical question answering over linked data, of the Question Answering over linked data challenge (QALD-4) [18] .  ... 
doi:10.3233/sw-160223 fatcat:5conapx3djafpcmhgyoyawusoq
« Previous Showing results 1 — 15 out of 424 results