86,431 Hits in 4.3 sec


Daniel Deutch, Nave Frost, Amir Gilad, Tomer Haimovich
2018 Proceedings of the VLDB Endowment  
Natural language (NL) interfaces to databases allow users without technical background to query the database and get the results.  ...  The explanations are shown in an intuitive manner, by highlighting parts of the original NL query that are intuitively "responsible" for the absence of the expected result.  ...  The user is then presented with the results of the initial query along with natural language explanations for the result set tuples, generated by NLProv.  ... 
doi:10.14778/3229863.3236241 fatcat:e7zcnudicjbfjdj2ob4ovxr5n4


Daniel Deutch, Nave Frost, Amir Gilad
2016 Proceedings of the VLDB Endowment  
We propose to present NLProv: an end-to-end Natural Language (NL) interface for database queries.  ...  The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only which are the results but also their explanations.  ...  We will first show the audience a single explanation for one of the answers, then consider all explanations and show the different variants of Natural Language explanations supported by the system: full  ... 
doi:10.14778/3007263.3007303 fatcat:zwbzltbxbbhehlufjupuxbla3a

Special issue on best papers of VLDB 2017

Peter Boncz, Kenneth Salem
2020 The VLDB journal  
In particular, they consider how to provide explanations, in natural language, of the answers to database queries that are posed in natural language.  ...  the results of their queries.  ...  As a result of its lightweight nature, Slalom is demonstrated to achieve efficient query processing over raw data minimal memory consumption.  ... 
doi:10.1007/s00778-019-00600-w fatcat:dlznp4dydzdknnlmlxeb4ei72e

R2D2: A Dbpedia Chatbot Using Triple-Pattern Like Queries

Haridimos Kondylakis, Dimitrios Tsirigotakis, Giorgos Fragkiadakis, Emmanouela Panteri, Alexandros Papadakis, Alexandros Fragkakis, Eleytherios Tzagkarakis, Ioannis Rallis, Zacharias Saridakis, Apostolos Trampas, Giorgos Pirounakis, Nikolaos Papadakis
2020 Algorithms  
In this paper, we present R2D2, an intelligent chatbot relying on semantic web technologies and offering an intelligent controlled natural language interface for accessing the information available in  ...  The queries are submitted to the corresponding DBpedia SPARQL endpoint, and then the result is received by R2D2 and augmented with maps and visuals and eventually presented to the user.  ...  in natural language from knowledge graphs [21] .  ... 
doi:10.3390/a13090217 fatcat:tvllkaq74fdltjazt3vmgxi6py

QUINT: Interpretable Question Answering over Knowledge Bases

Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, Gerhard Weikum
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations  
When QUINT answers a question, it visualizes the complete derivation sequence from the natural language utterance to the final answer.  ...  We present QUINT, a live system for question answering over knowledge bases. QUINT automatically learns role-aligned utterance-query templates from user questions paired with their answers.  ...  For example, for the utterance "What language group does English belong to?", 'English' gets mapped to the wrong entity England, resulting in an unexpected answer.  ... 
doi:10.18653/v1/d17-2011 dblp:conf/emnlp/AbujabalRYW17 fatcat:dektyvghuzhujfgmzeniq22iwm

The SQLX system: generating explanations for clinical rules encoded in SQL

W Sujansky, M Shwe
1992 Proceedings. Symposium on Computer Applications in Medical Care  
We have developed a system to provide case-specific explanations for SQL query results.  ...  The explanation facility, called SQLX, is intended to improve user acceptance of clinical rules that are encoded in the SQL query language and are triggered by updates to a relational database.  ...  The authors also would like to thank Lyn Dupre for her helpful editing comments.  ... 
pmid:1482874 pmcid:PMC2248127 fatcat:ergufogsp5fahajyuwhgwxba3i

e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations [article]

Clemens Rosenbaum, Tian Gao, Tim Klinger
2017 arXiv   pre-print
In response the User simulator provides a natural language explanation of why the Agent's query or answer was useful in narrowing down the set of possible answers, or not.  ...  At each turn the Agent may ask for the value of a variable or try to answer the challenge question.  ...  For future work, we would like to investigate whether we can train the net to generate natural language explanations and how this might affect prediction performance.  ... 
arXiv:1708.01776v1 fatcat:tzfwvgvwh5dbhjogxkedkfehvy

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge [article]

Rodrigo F. G. Silva, Chanchal K. Roy, Mohammad Masudur Rahman, Kevin A. Schneider, Klerisson Paixao, Marcelo de Almeida Maia
2019 arXiv   pre-print
Furthermore, we perform natural language processing on the top quality answers and then return such programming solutions containing code examples and code explanations unlike earlier studies.  ...  Developers often search for relevant code examples on the web for their programming tasks. Unfortunately, they face two major problems.  ...  ACKNOWLEDGEMENT We thank the authors of BIKER for sharing their tool.  ... 
arXiv:1903.07662v2 fatcat:ic7aix2klzeklhrier4hvop4xe

Why machines should analyse intention in natural language dialogue

1999 International Journal of Human-Computer Studies  
In turn, the hypothesis provides evidence for a theory of intention analysis for natural-language dialogue processing.  ...  MC KEVITT E¹ A¸. been on developing models for text and speech processing. Some work has concentrated more speci"cally on processing natural-language dialogue.  ...  The results can be verbalized in natural language.  ... 
doi:10.1006/ijhc.1999.0271 fatcat:rb4dyl3x3bgqdlsyoczhfzpfc4

Knowledge-based relational search in cultural heritage linked data

Eero Hyvönen, Heikki Rantala
2021 Digital Scholarship in the Humanities  
In this way, (1) semantically uninteresting connections can be ruled out effectively and (2) natural language explanations about the connections can be created for the end-user.  ...  This article presents a new knowledge-based approach for finding interesting semantic relations between resources in a knowledge graph (KG).  ...  Acknowledgements The authors wish to acknowledge CSC-IT Center for Science, Finland, for computational resources.  ... 
doi:10.1093/llc/fqab042 fatcat:vi2ml7vffrgnjkhbpueu6mpn4q

Page 82 of Computational Linguistics Vol. 23, Issue 1 [page]

1997 Computational Linguistics  
The planner passes the resulting explanation plan to the realization component (Section 6) for translation to natural language. The views in the explanation plan are grouped into paragraph clusters.  ...  Explanation generation terminates when the realization component has translated all of the views in the explanation plan to natural language. 5.2 The Explanation-Planning Algorithms The EXPLAIN algorithm  ... 

Explaining Causes Behind SQL Query Formulation Errors

Toni Taipalus
2020 2020 IEEE Frontiers in Education Conference (FIE)  
In order to more effectively teach query formulation, educators should emphasize natural language patterns, query planning, and increasingly ambiguous exercises.  ...  This Full Research Paper presents the most prominent query formulation errors in Structured Query Language (SQL), and maps these errors to their cognitive explanations.  ...  to the imperative nature of many programming languages studied [6] .  ... 
doi:10.1109/fie44824.2020.9274114 fatcat:hefky2uc45ei7klhitaw6qazhy

An Explanatory Query-Based Framework for Exploring Academic Expertise [article]

Oana Cocarascu, Andrew McLean, Paul French, Francesca Toni
2021 arXiv   pre-print
Given user queries in natural language, our framework finds researchers with relevant expertise, making use of domain-specific knowledge bases and word embeddings.  ...  It also generates explanations for its recommendations.  ...  The research was supported by Imperial College London's Faculty of Natural Sciences, Department of Computing and ICT.  ... 
arXiv:2105.13728v2 fatcat:3iqw4syxybcmlenmmowlpmtbs4

A Formal Language Approach to Explaining RNNs [article]

Bishwamittra Ghosh, Daniel Neider
2020 arXiv   pre-print
This paper presents LEXR, a framework for explaining the decision making of recurrent neural networks (RNNs) using a formal description language called Linear Temporal Logic (LTL).  ...  LTL is the de facto standard for the specification of temporal properties in the context of formal verification and features many desirable properties that make the generated explanations easy for humans  ...  Figure 2 : 2 Experimental results for twelve queries to a RNN for balanced parentheses. Figure 3 : 3 Experimental results for eleven queries to a RNN for the language F(a).  ... 
arXiv:2006.07292v1 fatcat:jsmw5bauxjbklb646dm2eyjphi


John W. S. Liu, Mariano P. Consens, Flavio Rizzolo
2006 Proceedings of the 2006 OOPSLA workshop on eclipse technology eXchange - eclipse '06  
The popularity of XML has motivated the development of novel XML processing tools many of which embed the XPath language for XML querying, transformation, constraint specification, etc.  ...  XPlainer-Eclipse combines editors for visualizing both XML documents and XPath expressions as trees together with the explanation of the answers.  ...  Financial support was provided by an Eclipse Innovation Award, an IBM Centre for Advanced Studies (CAS) Fellowship, and the Natural Sciences and Engineering Research Council (NSERC).  ... 
doi:10.1145/1188835.1188852 dblp:conf/eclipse/LiuCR06 fatcat:weab5vhalnbdlfxbqlldyr6wrm
« Previous Showing results 1 — 15 out of 86,431 results