In-context query reformulation for failing SPARQL queries

Viswanathan, Amar; Michaelis, James; Cassidy, Taylor; Mel, Geeth de; Hendler, James A.

doi:10.1117/12.2266590

Cited by 2 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The search in myDIG draws upon several independently-developed techniques in the IR community. Chief among these are query reformulation and constraint relaxation [25][26][27][28]. These techniques are designed to be robust to erroneous or missing data, which is an unavoidable problem for semi-automatic KGC systems.…”

Section: Information Retrievalmentioning

confidence: 99%

myDIG: Personalized Illicit Domain-Specific Knowledge Discovery with No Programming

Kejriwal

Szekely

2019

Future Internet

View full text Add to dashboard Cite

With advances in machine learning, knowledge discovery systems have become very complicated to set up, requiring extensive tuning and programming effort. Democratizing such technology so that non-technical domain experts can avail themselves of these advances in an interactive and personalized way is an important problem. We describe myDIG, a highly modular, open source pipeline-construction system that is specifically geared towards investigative users (e.g., law enforcement) with no programming abilities. The myDIG system allows users both to build a knowledge graph of entities, relationships, and attributes for illicit domains from a raw HTML corpus and also to set up a personalized search interface for analyzing the structured knowledge. We use qualitative and quantitative data from five case studies involving investigative experts from illicit domains such as securities fraud and illegal firearms sales to illustrate the potential of myDIG.

show abstract

Section: Information Retrievalmentioning

confidence: 99%

myDIG: Personalized Illicit Domain-Specific Knowledge Discovery with No Programming

Kejriwal

Szekely

2019

Future Internet

View full text Add to dashboard Cite

show abstract

“…Search in myDIG draws upon several independently developed techniques in the IR community. Chief among these are query reformulation and constraint relaxation (Rieh and others 2006), (Viswanathan et al 2017), (Muslea 2004), (Mirzadeh, Ricci, and Bansal 2004). These techniques are designed to be robust to erroneous or missing data, which is an unavoidable problem for semi-automatic KGC systems.…”

Section: Related Workmentioning

confidence: 99%

Constructing Domain-Specific Search Engines With No Programming

Kejriwal¹,

Szekely²

2018

AAAI

View full text Add to dashboard Cite

We propose a demonstration of myDIG (my Domain-specific Insight Graphs), a system that allows non-technical domain experts, including those with no programming experience, to construct a domain-specific search engine over a raw corpus of webpages. myDIG has been developed and refined over multiple years under the DARPA MEMEX program, and has undergone rigorous user testing with actual domain experts from investigative agencies like the Securities and Exchange Commission (SEC). All components of myDIG are open-source, and the product of fundamental research.

show abstract

In-context query reformulation for failing SPARQL queries

Cited by 2 publications

References 1 publication

myDIG: Personalized Illicit Domain-Specific Knowledge Discovery with No Programming

myDIG: Personalized Illicit Domain-Specific Knowledge Discovery with No Programming

Constructing Domain-Specific Search Engines With No Programming

Contact Info

Product

Resources

About