equal encyclopaedic qa for lists
play

EQUAL Encyclopaedic QA for Lists Iustin Dornescu Research Group in - PowerPoint PPT Presentation

Sep 25, 2023 •221 likes •365 views

Semantic QA: my vision for the future EQUAL Implementation details EQUAL Encyclopaedic QA for Lists Iustin Dornescu Research Group in Computational Linguistics, University of Wolverhampton, UK October 2, 2009 Iustin Dornescu CLEF

  1. Semantic QA: my vision for the future EQUAL – Implementation details EQUAL – Encyclopaedic QA for Lists Iustin Dornescu Research Group in Computational Linguistics, University of Wolverhampton, UK October 2, 2009 Iustin Dornescu CLEF 2009 Workshop

  2. Semantic QA: my vision for the future EQUAL – Implementation details GikiCLEF Complex question answering on Wikipedia. 50 multilingual list topics such as: GC-2009-06 Which Dutch violinists held the post of concertmaster at the Royal Concertgebouw Orchestra in the twentieth century? GC-2009-34 What eight-thousanders are at least partially in Nepal? Iustin Dornescu CLEF 2009 Workshop

  3. Semantic QA: my vision for the future EQUAL – Implementation details Encouraging results We need something radically different to standard textual QA Iustin Dornescu CLEF 2009 Workshop

  4. Semantic QA: my vision for the future EQUAL – Implementation details Outline Semantic QA: my vision for the future 1 EQUAL – Implementation details 2 Iustin Dornescu CLEF 2009 Workshop

  5. Semantic QA: my vision for the future EQUAL – Implementation details Semantic QA rEvolution Textual QA [web of] documents vs. web of data document retrieval vs. search for facts keywords & co-occurrence vs. concepts & relations textual snippet vs. graph patterns gazetteers vs. RDF Data text with entities vs. entities with text lexical semantics vs. formal semantics Semantic QA Iustin Dornescu CLEF 2009 Workshop

  6. Semantic QA: my vision for the future EQUAL – Implementation details Semantic QA representation represent Wikipedia using a semantic graph: entities characterised by types, attributes & properties, and connected to each other by relations a question is a composition of constraints about: entities their types their properties their relations finding answers means performing some actions from a given set (that the system understands) Iustin Dornescu CLEF 2009 Workshop

  7. Semantic QA: my vision for the future EQUAL – Implementation details Semantic QA Dev. topic Which football players from Brazil play in clubs from the Iberian Peninsula 1. identify Brazilian footballers 2. identify the club each of them plays for 3. test if the club is located in the Iberian Peninsula Iustin Dornescu CLEF 2009 Workshop

  8. Semantic QA: my vision for the future EQUAL – Implementation details Semantic QA Iustin Dornescu CLEF 2009 Workshop

  9. Semantic QA: my vision for the future EQUAL – Implementation details Analysis and Feedback A useful QA system must use the meaning, not the words: Analysis Phase Understand the information need behind the question detect different ambiguity sources create a semantic question interpretation for each ranking Feedback Phase Interact with the user allow user to disambiguate generate justification active learning Iustin Dornescu CLEF 2009 Workshop

  10. Semantic QA: my vision for the future EQUAL – Implementation details Outline Semantic QA: my vision for the future 1 EQUAL – Implementation details 2 Iustin Dornescu CLEF 2009 Workshop

  11. Semantic QA: my vision for the future EQUAL – Implementation details Analysis 1: EAT a) Use an ad-hoc classifier for chunk delimiters: the first chunk with a plural noun contains the EAT; List the Italian places where ... Which countries have... Name Romanian poets who... Which Dutch violinists who... In which European countries is... b) Find the best matching Wikipedia Category. Iustin Dornescu CLEF 2009 Workshop

  12. Semantic QA: my vision for the future EQUAL – Implementation details Analysis 2: Constraints Map the remaining chunks to semantic constraints: a) entity: ..“are at least partly in [[Nepal]]” b) category: ..“play in [[Spanish football clubs]]” c) property: ..“with a population larger than 100,000 people ” d) temporal: ..“in the twentieth century” e) geographic: ..“are at least partly in [[Nepal]]” Iustin Dornescu CLEF 2009 Workshop

  13. Semantic QA: my vision for the future EQUAL – Implementation details Analysis 3: Filters The actual implementation of a semantic constraint. infobox attributes categories definition external datasources article text (NLP) Iustin Dornescu CLEF 2009 Workshop

  14. Semantic QA: my vision for the future EQUAL – Implementation details Results EQUAL: 813 answers – 385(correct), 105(unjustified), 323(incorrect) P = 47 . 35 % ( 60 . 27 % ) R p = 27 . 20 % ( 34 . 62 % ) Total Answers: 1415 Iustin Dornescu CLEF 2009 Workshop

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Lecture 8: lists and searching Predicting l Let l = list(range(10)) . What does l equal after the

Lecture 8: lists and searching Predicting l Let l = list(range(10)) . What does l equal after the

Lecture 8: lists and searching Predicting l Let l = list(range(10)) . What does l equal after the following operations? l.append(11) del l[0] l.remove(1) Predicting l Let l = list(range(10)) . What does l equal after the following operations?

289 views • 7 slides
Equality: Are Some Equality: Are Some More Equal than than More Equal Others? Others? All

Equality: Are Some Equality: Are Some More Equal than than More Equal Others? Others? All

Equality: Are Some Equality: Are Some More Equal than than More Equal Others? Others? All animals are equal, but some animals are more equal than others. Orwell, G. (2004). Animal farm. New York: Signet. United States Bill of Rights

177 views • 13 slides
Equal Value: How do We Get There? The Presentation Equal Pay and UN Global Compact

Equal Value: How do We Get There? The Presentation Equal Pay and UN Global Compact

Equal Pay for Work of Equal Value: How do We Get There? The Presentation Equal Pay and UN Global Compact Principles The concept of Equal Pay Advantages of Equal Pay The gender pay gap in numbers Why a gender pay gap?

303 views • 29 slides
K EY INSIGHTS FROM EQUAL EQUAL funding (particularly under the Adaptability pillar) has provided

K EY INSIGHTS FROM EQUAL EQUAL funding (particularly under the Adaptability pillar) has provided

EQUAL PAVES THE WAY FOR SOCIALLY RESPONSIBLE RESTRUCTURING In a recent presentation to the CEDEFOP[1] conference on Guidance for Workforce Development , held in Thessaloniki on 25/26 June 2007, the EQUAL programme had the opportunity to present its

341 views • 3 slides
More lists Readings: HtDP , sections 11, 12, 13 (Intermezzo 2). Topics: Sorting a list List

More lists Readings: HtDP , sections 11, 12, 13 (Intermezzo 2). Topics: Sorting a list List

More lists Readings: HtDP , sections 11, 12, 13 (Intermezzo 2). Topics: Sorting a list List abbreviations Lists containing lists Dictionaries and association lists Lists of lists as 2D data Processing two lists simultaneously Consuming a

712 views • 25 slides
Proofs about functions Function consuming A is related to proof about A Q: How to prove two

Proofs about functions Function consuming A is related to proof about A Q: How to prove two

Proofs about functions Function consuming A is related to proof about A Q: How to prove two lists are equal? A: Prove they are both () or that they are both cons cells cons-ing equal cars to equal cdrs Q: How to prove two

224 views • 20 slides
Red Lists and Red Books in Poland Main characteristics: 1. Red Lists lists of species with

Red Lists and Red Books in Poland Main characteristics: 1. Red Lists lists of species with

Red Lists and Red Books in Poland Main characteristics: 1. Red Lists lists of species with threat category 2. Red Books list of species with much more information on the species (distribution, habitat, morphology, ecology, maps etc.) 3.

294 views • 4 slides
Pay Equity Law Federal Equal Pay Act Employers are required to provide equal pay for men and

Pay Equity Law Federal Equal Pay Act Employers are required to provide equal pay for men and

October 24, 2019 Pay Equity Law Federal Equal Pay Act Employers are required to provide equal pay for men and women for jobs within the same establishment that require: equal skill, effort and responsibility, and are performed under

629 views • 39 slides
Nested Lists Nested Lists Lists can hold any object Lists are themselves objects

Nested Lists Nested Lists Lists can hold any object Lists are themselves objects

Mini-Lecture 16 Nested Lists Nested Lists Lists can hold any object Lists are themselves objects Therefore lists can hold other lists! x[2] a = [2, 1] x[1] x[2][2] b = [3, 1] x = [1, [2, 1], [1, 4, [3, 1]], 5] c = [1, 4, b]

586 views • 14 slides
13-1 Exercise Implementing Lists with Linked Lists First, lets augment our node class

13-1 Exercise Implementing Lists with Linked Lists First, lets augment our node class

Overview Topics Nodes and Links List implementation using linked lists CSE 143 Java Autumn 2001 Reading: Textbook: Ch. 23 Linked Lists 11/19/2001 (c) 2001, University of Washington 13-1 11/19/2001 (c) 2001,

333 views • 4 slides
European Quadricycles League (EQUAL) United- Kingdom PRESENTATION OF EQUAL EQUAL is the European

European Quadricycles League (EQUAL) United- Kingdom PRESENTATION OF EQUAL EQUAL is the European

European Quadricycles League (EQUAL) United- Kingdom PRESENTATION OF EQUAL EQUAL is the European association of manufacturers of quadricycles. We Represent key quadricycle manufacturers whos facilities are primarily based in France and Italy.

256 views • 10 slides
Py Python Lists Similar to an array but some important differences: lists do not have a fixed

Py Python Lists Similar to an array but some important differences: lists do not have a fixed

2/5/20 Py Python Lists Similar to an array but some important differences: lists do not have a fixed size lists are heterogeneous can insert delete at arbitrary positions within list CS 224 Introduction to Python Spring 2020

400 views • 6 slides
Nested Lists Motivating this Course Module In previous video series, introduced lists All

Nested Lists Motivating this Course Module In previous video series, introduced lists All

Module 18 Nested Lists Motivating this Course Module In previous video series, introduced lists All our examples had primitives in the lists So we only showed one folder in visualization Demo: x = [5,6,5,9] But lists can contain

607 views • 24 slides
Introduction to Object-Oriented Programming Linked Lists Christopher Simpkins

Introduction to Object-Oriented Programming Linked Lists Christopher Simpkins

Introduction to Object-Oriented Programming Linked Lists Christopher Simpkins chris.simpkins@gatech.edu CS 1331 (Georgia Tech) 1 / 13 Linked Lists Linked Lists Dynamic data structures Singly linked lists Generic linked lists Doubly linked

179 views • 13 slides
Using Lists and Tables Student Web Presence Guidelines Summary 1. Purpose of lists 2. Using

Using Lists and Tables Student Web Presence Guidelines Summary 1. Purpose of lists 2. Using

Using Lists and Tables Student Web Presence Guidelines Summary 1. Purpose of lists 2. Using lists 3. Using bulleted list 4. Using ordered lists 5. Purpose of tables 6. Using tables The Purpose of Lists Take up less space Improve

238 views • 9 slides
csci 210: Data Structures Linked lists Summary Today linked lists single-linked

csci 210: Data Structures Linked lists Summary Today linked lists single-linked

csci 210: Data Structures Linked lists Summary Today linked lists single-linked lists double-linked lists circular lists READING: LC chapter 4.1, 4.2, 4.3 Arrays vs. Linked Lists We ve seen arrays:

617 views • 34 slides
Automatically Annotating Text with Linked Open Data Delia Rusu , Bla Fortuna, Dunja Mladeni

Automatically Annotating Text with Linked Open Data Delia Rusu , Bla Fortuna, Dunja Mladeni

Automatically Annotating Text with Linked Open Data Delia Rusu , Bla Fortuna, Dunja Mladeni Joef Stefan Institute ailab.ijs.si Motivation: Annotating Text with LOD DBpedia Open Cyc WordNet ailab.ijs.si Overview Related work

429 views • 17 slides
Taaltheorie en Taalverwerking BSc Artificial Intelligence Raquel Fernndez Institute for Logic,

Taaltheorie en Taalverwerking BSc Artificial Intelligence Raquel Fernndez Institute for Logic,

Taaltheorie en Taalverwerking BSc Artificial Intelligence Raquel Fernndez Institute for Logic, Language, and Computation Winter 2012, lecture 3b Raquel Fernndez TtTv 2012 - lecture 3b 1 / 19 Plan for Today Theoretical session: PCFGs

585 views • 36 slides
The C standard formalized in Coq, whats next? Robbert Krebbers Aarhus University, Denmark

The C standard formalized in Coq, whats next? Robbert Krebbers Aarhus University, Denmark

The C standard formalized in Coq, whats next? Robbert Krebbers Aarhus University, Denmark May 13, 2016 @ Cambridge Computer Laboratory, UK 1 What is this program supposed to do? The C quiz, question 1 int main() { int x; int y = (x = 3)

1.2k views • 75 slides
The Dual Simplex Method Combinatorial Problem Solving (CPS) Javier Larrosa Albert Oliveras

The Dual Simplex Method Combinatorial Problem Solving (CPS) Javier Larrosa Albert Oliveras

The Dual Simplex Method Combinatorial Problem Solving (CPS) Javier Larrosa Albert Oliveras Enric Rodr guez-Carbonell April 24, 2020 Basic Idea Abuse of terminology: Henceforth sometimes by optimal we will mean satisfying

711 views • 50 slides
Action recognition Cordelia Schmid INRIA Grenoble Action recognition examples Short

Action recognition Cordelia Schmid INRIA Grenoble Action recognition examples Short

Action recognition Cordelia Schmid INRIA Grenoble Action recognition examples Short actions, i.e. answer phone, shake hands answer phone hand shake Hollywood dataset Action recognition examples Activities/events, i.e.

615 views • 18 slides
PostgreSQL, pgAdmin, and JOINs PDBM 7.37.3.1.5 Dr. Chris Mayfield Department of Computer

PostgreSQL, pgAdmin, and JOINs PDBM 7.37.3.1.5 Dr. Chris Mayfield Department of Computer

PostgreSQL, pgAdmin, and JOINs PDBM 7.37.3.1.5 Dr. Chris Mayfield Department of Computer Science James Madison University Feb 06, 2020 What is PostgreSQL? PostgreSQL is a powerful, open source object-relational database system. . .

768 views • 18 slides
Photon BackTracker in LArSoft J. Stock, J Reichenbacher. South Dakota School of Mines and

Photon BackTracker in LArSoft J. Stock, J Reichenbacher. South Dakota School of Mines and

Photon BackTracker in LArSoft J. Stock, J Reichenbacher. South Dakota School of Mines and Technology. December 14, 2016. Photon Detector Sim/Reco Meeting./SNB-LowEnergy Meeting Why do we need Photon Backtracking? Position Studies. The

677 views • 14 slides
Lazy Spilling for a Time-Predictable Stack Cache: Implementation and Analysis Sahar Abbaspour,

Lazy Spilling for a Time-Predictable Stack Cache: Implementation and Analysis Sahar Abbaspour,

Lazy Spilling for a Time-Predictable Stack Cache: Implementation and Analysis Sahar Abbaspour, Alexander Jordan Florian Brandner Embedded Systems Engineering Sect. Unit e dInformatique et dIng. des Syst` emes Technical University of

805 views • 80 slides

More recommend