 General domain question answering system.  The starting point was the architecture described in Brill, Eric. ‘Processing Natural Language without Natural.

Slides:



Advertisements
Similar presentations
SINAI-GIR A Multilingual Geographical IR System University of Jaén (Spain) José Manuel Perea Ortega CLEF 2008, 18 September, Aarhus (Denmark) Computer.
Advertisements

Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling Mihai Surdeanu with a lot help from: Hoa Dang, Joe Ellis, Heng Ji, and.
DOMAIN DEPENDENT QUERY REFORMULATION FOR WEB SEARCH Date : 2013/06/17 Author : Van Dang, Giridhar Kumaran, Adam Troy Source : CIKM’12 Advisor : Dr. Jia-Ling.
Group Members: Satadru Biswas ( ) Tanmay Khirwadkar ( ) Arun Karthikeyan Karra (05d05020) CS Course Seminar Group-2 Question Answering.
CLEF 2008 Multilingual Question Answering Track UNED Anselmo Peñas Valentín Sama Álvaro Rodrigo CELCT Danilo Giampiccolo Pamela Forner.
Multilingual experiments of CLEF 2003 Eija Airio, Heikki Keskustalo, Turid Hedlund, Ari Pirkola University of Tampere, Finland Department of Information.
Q/A System First Stage: Classification Project by: Abdullah Alotayq, Dong Wang, Ed Pham.
Chapter 11 Beyond Bag of Words. Question Answering n Providing answers instead of ranked lists of documents n Older QA systems generated answers n Current.
Question-Answering: Overview Ling573 Systems & Applications March 31, 2011.
Information and Communication Technologies 1 Esfinge (Sphinx) at CLEF 2008: Experimenting with answer retrieval patterns. Can they help? Luís Fernando.
Cross Language IR Philip Resnik Salim Roukos Workshop on Challenges in Information Retrieval and Language Modeling Amherst, Massachusetts, September 11-12,
The Informative Role of WordNet in Open-Domain Question Answering Marius Paşca and Sanda M. Harabagiu (NAACL 2001) Presented by Shauna Eggers CS 620 February.
Employing Two Question Answering Systems in TREC 2005 Harabagiu, Moldovan, et al 2005 Language Computer Corporation.
The Social Web: A laboratory for studying s ocial networks, tagging and beyond Kristina Lerman USC Information Sciences Institute.
With or without users? Julio Gonzalo UNEDhttp://nlp.uned.es.
Overview of Search Engines
 Official Site: facility.org/research/evaluation/clef-ip-10http:// facility.org/research/evaluation/clef-ip-10.
Search is not only about the Web An Overview on Printed Documents Search and Patent Search Walid Magdy Centre for Next Generation Localisation School of.
Spanish Question Answering Evaluation Anselmo Peñas, Felisa Verdejo and Jesús Herrera UNED NLP Group Distance Learning University of Spain CICLing 2004,
CS598CXZ Course Summary ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign.
Powered by (How) do you use social Media?ESO/Cancer World survey Friday, November 14, 2014.
CLEF – Cross Language Evaluation Forum Question Answering at CLEF 2003 ( Bridging Languages for Question Answering: DIOGENE at CLEF-2003.
A Technical Seminar on Question Answering SHRI RAMDEOBABA COLLEGE OF ENGINEERING & MANAGEMENT Presented By: Rohini Kamdi Guided By: Dr. A.J.Agrawal.
THE ROLE OF ADAPTIVE ELEMENTS IN WEB-BASED SURVEILLANCE SYSTEM USER INTERFACES RICARDO LAGE, PETER DOLOG, AND MARTIN LEGINUS
Log on to Digital Locker Website You should be able to log on using Internet Explorer browser at the campus. You may need to log in using Mozilla FireFox.
AnswerBus Question Answering System Zhiping Zheng School of Information, University of Michigan HLT 2002.
Chapter 2 Architecture of a Search Engine. Search Engine Architecture n A software architecture consists of software components, the interfaces provided.
Question Answering.  Goal  Automatically answer questions submitted by humans in a natural language form  Approaches  Rely on techniques from diverse.
Answer Validation Exercise - AVE QA subtrack at Cross-Language Evaluation Forum UNED (coord.) Anselmo Peñas Álvaro Rodrigo Valentín Sama Felisa Verdejo.
MIRACLE Multilingual Information RetrievAl for the CLEF campaign DAEDALUS – Data, Decisions and Language, S.A. Universidad Carlos III de.
A Language Independent Method for Question Classification COLING 2004.
21/11/2002 The Integration of Lexical Knowledge and External Resources for QA Hui YANG, Tat-Seng Chua Pris, School of Computing.
$1,000,000 $500,000 $100,000 $50,000 $10,000 $5000 $1000 $500 $200 $100 Is this your Final Answer? YesNo Question 2? Correct Answer Wrong Answer.
Lucene-Demo Brian Nisonger. Intro No details about Implementation/Theory No details about Implementation/Theory See Treehouse Wiki- Lucene for additional.
D L T Cross-Language French-English Question Answering using the DLT System at CLEF 2003 Aoife O’Gorman Igal Gabbay Richard F.E. Sutcliffe Documents and.
Object-Oriented Software Engineering using Java, Patterns &UML. Presented by: E.S. Mbokane Department of System Development Faculty of ICT Tshwane University.
A Novel Pattern Learning Method for Open Domain Question Answering IJCNLP 2004 Yongping Du, Xuanjing Huang, Xin Li, Lide Wu.
BioRAT: Extracting Biological Information from Full-length Papers David P.A. Corney, Bernard F. Buxton, William B. Langdon and David T. Jones Bioinformatics.
GeoCLEF Breakout Notes Fred Gey, Ray Larson, Paul Clough.
Exploiting Wikipedia Categorization for Predicting Age and Gender of Blog Authors K Santosh Aditya Joshi Manish Gupta Vasudeva Varma
LING 573 Deliverable 3 Jonggun Park Haotian He Maria Antoniak Ron Lockwood.
Department of Software and Computing Systems Research Group of Language Processing and Information Systems The DLSIUAES Team’s Participation in the TAC.
Which Log for which Information? Gathering Multilinguality Data from Different Log File Types Maria Gäde, Vivien Petras, and Juliane Stiller Humboldt-Universität.
1 Flexible and Efficient Toolbox for Information Retrieval MIRACLE group José Miguel Goñi-Menoyo (UPM) José Carlos González-Cristóbal (UPM-Daedalus) Julio.
Thomas Mandl: GeoCLEF Track Overview Cross-Language Evaluation Forum (CLEF) Thomas Mandl, (U. Hildesheim) 8 th Workshop.
One Click One Revisited: Enhancing Evaluation Based on Information Units Tetsuya Sakai 1 and Makoto P. Kato 2 1 Microsoft Research Asia, P.R. China
Date: 2013/10/23 Author: Salvatore Oriando, Francesco Pizzolon, Gabriele Tolomei Source: WWW’13 Advisor: Jia-ling Koh Speaker: Chen-Yu Huang SEED:A Framework.
CharMeck.org Contributer Training SharePoint 2013 Orientation and Basic Training.
Evaluating Answer Validation in multi- stream Question Answering Álvaro Rodrigo, Anselmo Peñas, Felisa Verdejo UNED NLP & IR group nlp.uned.es The Second.
How to Program? -- Part 1 Part 1: Problem Solving –Analyze a problem –Decide what steps need to be taken to solve it. –Take into consideration any special.
Comparing Document Segmentation for Passage Retrieval in Question Answering Jorg Tiedemann University of Groningen presented by: Moy’awiah Al-Shannaq
Answer Mining by Combining Extraction Techniques with Abductive Reasoning Sanda Harabagiu, Dan Moldovan, Christine Clark, Mitchell Bowden, Jown Williams.
公司 標誌 Question Answering System Introduction to Q-A System 資訊四 B 張弘霖 資訊四 B 王惟正.
AQUAINT AQUAINT Evaluation Overview Ellen M. Voorhees.
Achieving Semantic Interoperability at the World Bank Designing the Information Architecture and Programmatically Processing Information Denise Bedford.
SEMANTIC VERIFICATION IN AN ONLINE FACT SEEKING ENVIRONMENT DMITRI ROUSSINOV, OZGUR TURETKEN Speaker: Li, HueiJyun Advisor: Koh, JiaLing Date: 2008/5/1.
Schools-On-I-Net and Google Apps for Education. Good-bye Yellow, Hello Blue Effective July 1, 2008.
Analysis of Experiments on Hybridization of different approaches in mono and cross-language information retrieval DAEDALUS – Data, Decisions and Language,
Web 2.0 Tools. Podcasts are an audio broadcast which has been converted to an mp3 file for playback in a digital music player. Podcast can be solicited.
Integrating linguistic knowledge in passage retrieval for question answering J¨org Tiedemann Alfa Informatica, University of Groningen HLT/EMNLP 2005.
General Architecture of Retrieval Systems 1Adrienn Skrop.
Link Distribution on Wikipedia [0422]KwangHee Park.
CLEF Budapest1 Measuring the contribution of Word Sense Disambiguation for QA Proposers: UBC: Agirre, Lopez de Lacalle, Otegi, Rigau, FBK: Magnini.
Search Engine Architecture
System Analysis and Design Task 1- Explanation
Bookkeeping Services Melbourne
Question Answer System Deliverable #2
How to Register For Access
CLEF 2008 Multilingual Question Answering Track
How to Register For Access
Presentation transcript:

 General domain question answering system.  The starting point was the architecture described in Brill, Eric. ‘Processing Natural Language without Natural Language Processing’, in A. Gelbukh (ed.), CICLing 2003, LNCS 2588, Springer-Verlag Berlin Heidelberg, 2003, pp : - Exploring the redundancy existent in the Web. - Exploring the fact that Portuguese is one of the most used languages in the Web.  Available on the Web.  Participation at CLEF 2004 and Two strategies were tested: - Searching the answers in the Web and using the CLEF document collection to confirm them (Strategy 1). - Searching the answers only in the CLEF document collection (Strategy 2).  Additional experiments using Strategy 1 were performed after error analysis and system debugging (Post-CLEF). 20th Century Esfinge (Sphinx) solving the riddles at CLEF 2005 Luís Costa Linguateca / SINTEF ICT PB 124, Blindern NO-0314 Oslo, Norway ? Question reformulation module Passage extraction from CLEF document collection Submition of answer patterns to Google Passages N-gram Harvesting TaskExperiment# questions# right% right CLEF 2005 PT-PT Strategy *24 % Strategy % Post-CLEF % EN-PT Strategy % CLEF 2004 PT-PT Strategy % Strategy % Post-CLEF % Esfinge overview What was new at CLEF 2005?  The results in the runs using the Web (Strategy 1) were slightly better than the runs using only the CLEF document collection on both participations.  The results using Strategy 2 for the questions of type People and Date are better both comparing to the other types of questions and to the same type of questions using Strategy 1. This suggests that both strategies are still worthwhile to experiment and study further.  The analysis of the individual modules shows that the NER system helps the system mainly in the questions of type “People”, “Quantity” and “Date”, while the morphological analyser is more influential in the questions of type “Which X”, “Who was ” and “What is”.  The results show that Esfinge improved comparing to last year: the results are better both with this year’s and last year’s questions. No => Stem patterns Stemmed Pattern 1 Stemmed Pattern n Answer = NIL No Passage extraction from CLEF document collection No Yes Yes => SIEMES NER No N-grams Filters (B+C+D) No Yes Answer = best scored N-gram YesNo Answer = NIL  Use of the named entity recognizer SIEMES (detection of humans, countries, settlements, geographical locations, dates and quantities).  List of not interesting websites (jokes, blogs, etc.)  Available Brazilian Portuguese document collection.  Use of the stemmer Lingua::PT::Stemmer for the generalization of search patterns.  Filtering of “undesired answers”. A list of these answers was built based on the logs of last year’s participation and tests performed afterwards.  Searching longer answers: the system does not stop when it finds an acceptable answer. Instead keeps searching for longer acceptable answers containing the latter.  Participation in the EN-PT multilingual task.  Correction of problems detected last year. * Two further right answers were found after the official results were released. Esfinge’s performance Filters (A+B+C+D) Esfinge on the Web Any N-grams? Doc.s Found? Q. pattern enables use of NER? Doc.s Found? Filters: A: Interesting PoS B: Answer contained in question C: Undesired answer D: Supporting document Doc.s Found? Any N-grams? Strategy 1 Answer Pattern 1 Answer Pattern n Strategy 2