Query Processing and Reasoning How Useful are Natural Language Interfaces to the Semantic Web for Casual End-users? Esther Kaufmann and Abraham Bernstein.

Slides:



Advertisements
Similar presentations
Natural Language Interfaces to Ontologies Danica Damljanović
Advertisements

Danica Damljanović University of Sheffield
CH-4 Ontologies, Querying and Data Integration. Introduction to RDF(S) RDF stands for Resource Description Framework. RDF is a standard for describing.
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
A Visual Approach to Semantic Query Design Using a Web-Based Graphical Query Designer Paul R. Smart, Alistair Russell, Dave Braines, Yannis Kalfoglou,,
02/04/09Danica Damljanović1 Natural Language Interfaces to conceptual models: usability and performance Danica Damljanović
UNIT-III By Mr. M. V. Nikum (B.E.I.T). Programming Language Lexical and Syntactic features of a programming Language are specified by its grammar Language:-
CHAITALI GUPTA, RAJDEEP BHOWMIK, MICHAEL R. HEAD, MADHUSUDHAN GOVINDARAJU, WEIYI MENG PRESENTED BY: SIDDHARTH PALANISWAMI A Query-based System for Automatic.
Dialogue – Driven Intranet Search Suma Adindla School of Computer Science & Electronic Engineering 8th LANGUAGE & COMPUTATION DAY 2009.
1 Towards Automating Complex Associative Access to Multiple Bioinformatics Data Sources Ling Liu, Calton Pu David Buttler, Wei Han Henrique Paques, Dan.
Information Retrieval in Practice
IR & Metadata. Metadata Didn’t we already talk about this? We discussed what metadata is and its types –Data about data –Descriptive metadata is external.
NaLIX: A Generic Natural Language Search Environment for XML Data Presented by: Erik Mathisen 02/12/2008.
Visual Web Information Extraction With Lixto Robert Baumgartner Sergio Flesca Georg Gottlob.
CMSC838 Project Presentation An Ontology-based Approach for Managing Software Components by Vladimir Kolovski.
1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central.
Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang National Central University
Interfaces for Querying Collections. Information Retrieval Activities Selecting a collection –Lists, overviews, wizards, automatic selection Submitting.
Ontology-Based Free-Form Query Processing for the Semantic Web Mark Vickers Brigham Young University MS Thesis Defense Supported by:
Semi-Automatic Learning of Transfer Rules for Machine Translation of Low-Density Languages Katharina Probst April 5, 2002.
1 DCS861A-2007 Emerging IT II Rinaldo Di Giorgio Andres Nieto Chris Nwosisi Richard Washington March 17, 2007.
Enhance legal retrieval applications with an automatically induced knowledge base Ka Kan Lo.
Overview of Search Engines
ANSWERING CONTROLLED NATURAL LANGUAGE QUERIES USING ANSWER SET PROGRAMMING Syeed Ibn Faiz.
Intelligent Tutoring Systems Traditional CAI Fully specified presentation text Canned questions and associated answers Lack the ability to adapt to students.
9/30/2004TCSS588A Isabelle Bichindaritz1 Introduction to Bioinformatics.
Aurora: A Conceptual Model for Web-content Adaptation to Support the Universal Accessibility of Web-based Services Anita W. Huang, Neel Sundaresan Presented.
©Silberschatz, Korth and Sudarshan5.1Database System Concepts Chapter 5: Other Relational Languages Query-by-Example (QBE) Datalog.
ITCS 6010 SALT. Speech Application Language Tags (SALT) Speech interface markup language Extension of HTML and other markup languages Adds speech and.
Chapter 10: Compilers and Language Translation Invitation to Computer Science, Java Version, Third Edition.
Introduction to MDA (Model Driven Architecture) CYT.
Trisolda Jakub Yaghob Charles University in Prague, Czech Rep.
A Survey for Interspeech Xavier Anguera Information Retrieval-based Dynamic TimeWarping.
Models for Language Engineering Bruno F. Barroca.
CORPORUM-OntoExtract Ontology Extraction Tool Author: Robert Engels Company: CognIT a.s.
Chapter 6 Programming Languages (2) Introduction to CS 1 st Semester, 2015 Sanghyun Park.
©2003 Paula Matuszek CSC 9010: Text Mining Applications Document Summarization Dr. Paula Matuszek (610)
The Internet 8th Edition Tutorial 4 Searching the Web.
Searching the web Enormous amount of information –In 1994, 100 thousand pages indexed –In 1997, 100 million pages indexed –In June, 2000, 500 million pages.
4 1 SEARCHING THE WEB Using Search Engines and Directories Effectively New Perspectives on THE INTERNET.
Natural Language Processing Menu Based Natural Language Interfaces -Kyle Neumeier.
Natural Language Programming David Vadas The University of Sydney Supervisor: James Curran.
User Profiling using Semantic Web Group members: Ashwin Somaiah Asha Stephen Charlie Sudharshan Reddy.
Shridhar Bhalerao CMSC 601 Finding Implicit Relations in the Semantic Web.
Topic Maps introduction Peter-Paul Kruijsen CTO, Morpheus software ISOC seminar, april 5 th 2005.
Aim Ability to automate the detection of financial inconsistency and irregularity Problem Need to create a unified and logically rigorous terminology.
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 1 (03/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Introduction to Natural.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
Natural Language Interfaces to Ontologies Danica Damljanović
Concepts and Realization of a Diagram Editor Generator Based on Hypergraph Transformation Author: Mark Minas Presenter: Song Gu.
A Portrait of the Semantic Web in Action Jeff Heflin and James Hendler IEEE Intelligent Systems December 6, 2010 Hyewon Lim.
University of Florida’s dchecker: Software for ensuring semantic data integrity Nicholas Rejack, MS 1, Christopher P. Barnes 1, Michael Conlon, PhD 2
Semantic Wiki: Automating the Read, Write, and Reporting functions Chuck Rehberg, Semantic Insights.
Module 2: Authoring Basic Reports. Overview Creating a Basic Table Report Formatting Report Pages Calculating Values.
Chapter 04 Semantic Web Application Architecture 23 November 2015 A Team 오혜성, 조형헌, 권윤, 신동준, 이인용.
GoRelations: an Intuitive Query System for DBPedia Lushan Han and Tim Finin 15 November 2011
Rule-based Reasoning in Semantic Text Analysis
3.1 Fundamentals of algorithms
Approaches to Machine Translation
DATA INTEGRATION FOR LANGUAGE DOCUMENTATION
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
improve the efficiency, collaborative potential, and
Query Construct Interfaces of RDF Data an introduction
Extracting Semantic Concept Relations
Approaches to Machine Translation
Question Answering & Linked Data
Khadija Elbedweihy, Stuart N. Wrigley, and Fabio Ciravegna
Chapter 10: Compilers and Language Translation
Chaitali Gupta, Madhusudhan Govindaraju
Presentation transcript:

Query Processing and Reasoning How Useful are Natural Language Interfaces to the Semantic Web for Casual End-users? Esther Kaufmann and Abraham Bernstein Presented By Stephen Lynn

Query Processing and Reasoning Overview  Natural Language Interfaces  Goals/Objectives  Introduce 4 Interfaces  Experiment  Evaluation Results  Future Work

Query Processing and Reasoning Natural Language Interfaces  Plain text queries  Phrases  Full Sentences  Challenges  Linguistic Variability (ambiguous meaning)  Domain Independence  Retrieval Performance (linked to portability)  Usefulness of NLIs

Query Processing and Reasoning Goals/Objectives Usability of NLIs Usefulness of NLIs

Query Processing and Reasoning Evaluation Interfaces  Portable  Domain-Independent  Good Performance  4 Interfaces  Least to Most Restrictive

Query Processing and Reasoning NLP-Reduce  Free-form text query  Remove Stop Words/Puncuation  Word Stemming  Identify Triple Structures (no details)  Enhanced Triple Store (WordNet)  Generate SPARQL  Return Results

Query Processing and Reasoning NLP-Reduce

Query Processing and Reasoning Querix  Parse Query  Extract Query Skeleton from Syntax Tree  Identifies Triple Patterns  Match Triples to Knowledge Base Resources  Generate SPARQL  Enhanced with WordNet Synonyms  Return Results

Query Processing and Reasoning Querix

Query Processing and Reasoning Querix – Ambiguity Resolution  What is the biggest state in the US?

Query Processing and Reasoning Ginseng  UI based on a grammar  Built dynamically from target knowledgebases  Incremental Parser  Offer possible completions (code completion)  Only accepts entries in list  No invalid queries  Convert to SPARQL  Return Results

Query Processing and Reasoning Ginseng

Query Processing and Reasoning Symantic Crystal  Graphical Display of Ontology  Select Elements in Ontology  No Invalid Queries  Specify Constraints  Incrementally Build Query  Generate SPARQL  Return Results

Query Processing and Reasoning Semantic Crystal

Query Processing and Reasoning Usability Study  How usable and useful are NLI applications?  Setup  48 subjects  4 interfaces  Same 4 questions for each interface (minor changes)  Area of Alaska?  Number of lakes in Florida?  States that have city named Springfield?  Rivers run through state that has largest city in US?  Change sequence of interfaces

Query Processing and Reasoning Experiment 1.Read Introduction Notes 2.Instructions on Interface #1 3.Answer 4 questions with interface 4.Fill out Usability survey about Interface 5.Repeat 2-4 for other Interfaces 6.Fill out Comparison Questionnaire

Query Processing and Reasoning Evaluation Results

Query Processing and Reasoning Evaluation Results

Query Processing and Reasoning Strengths  Good General Points  Automation is good (not Sematic Crystal)  Result format affects user trust  Balance between freedom and restriction  User Evaluation  Analysis

Query Processing and Reasoning Weaknesses  Completion time not a deciding factor in satisfaction  Still pushing Semantic Crystal  Personal Attachment  Unclear distinction between QL and Interface

Query Processing and Reasoning Future Work  Compare with more NLIs  Multiple Domains  Single Infrastructure w/Different Uis  Evaluate Usability/Usefulness