Kees van Deemter Generation of Referring Expressions: a crash course Background information and Project HIT 2010.

Slides:



Advertisements
Similar presentations
Building a Career Portfolio
Advertisements

Close Reading at NQ Is it really that different to what I have done before?
Kees van Deemter Matthew Stone Formal Issues in Natural Language Generation Lecture 4 Shieber 1993; van Deemter 2002.
Generation of Referring Expressions: the State of the Art SELLC Summer School, Harbin 2010 Kees van Deemter Computing Science University of Aberdeen.
Generation of Referring Expressions: the State of the Art LOT Winter School, Tilburg 2008 Kees van Deemter Computing Science University of Aberdeen.
Data Collection Strategies An Overview. How Do We Assess ?
Project Analysis Course ( ) Final Project Report Overview.
CS4018 Formal Models of Computation weeks Computability and Complexity Kees van Deemter (partly based on lecture notes by Dirk Nikodem)
Using the IDEA Student Ratings System: An Introduction University of Saint Thomas Fall
Student Manager Catalog Builder An ACEware Webinar.
Test-Taking Strategies
Journal Entry 1 Focus: Rhetorical appeals
Some Practical Steps to Test Construction
Information Retrieval in Practice
Search Engines and Information Retrieval
ETT 229 Fall 2004 Web Design Basics II. Agenda 11:00-11:05 – Quiz 14 11:05-11:50 – Web Design Lecture 11:50-12:15 – Web Design Practice 2.
LinkSelector: A Web Mining Approach to Hyperlink Selection for Web Portals Xiao Fang University of Arizona 10/18/2002.
Properties of Text CS336 Lecture 3:. 2 Information Retrieval Searching unstructured documents Typically text –Newspaper articles –Web pages Other documents.
Software Requirements
The aim of this part of the curriculum design process is to find the situational factors that will strongly affect the course.
©Ian Sommerville 2000 Software Engineering, 6th edition. Chapter 5 Slide 1 Requirements engineering l The process of establishing the services that the.
Preparing for the Verbal Reasoning Measure. Overview Introduction to the Verbal Reasoning Measure Question Types and Strategies for Answering General.
Overview of Search Engines
Software Documentation Written By: Ian Sommerville Presentation By: Stephen Lopez-Couto.
Transfer Equivalency Lookup on the Web Jill Jerome Network Manager Undergraduate Admission University of Georgia.
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
Scenario testing Tor Stålhane. Scenario testing – 1 There are two types of scenario testing. Type 1 – scenarios used as to define input/output sequences.
Introduction CSE 1310 – Introduction to Computers and Programming
CSCI 347 – Data Mining Lecture 01 – Course Overview.
Project Analysis Course ( ) Final Project Report Overview Prepared by: Sijali Petro Korojelo (Course Assistant)
Search Engines and Information Retrieval Chapter 1.
IMSS005 Computer Science Seminar
Date: 2012/10/18 Author: Makoto P. Kato, Tetsuya Sakai, Katsumi Tanaka Source: World Wide Web conference (WWW "12) Advisor: Jia-ling, Koh Speaker: Jiun.
MIS 2000 Chapter 1: Managing the Digital Firm. IS for Management Outline Digital Firm Data, Information, Knowledge Information System (IS) IS User Information.
C HU H AI C OLLEGE O F H IGHER E DUCATION D EPARTMENT O F C OMPUTER S CIENCE Preparation of Final Year Project Report Bachelor of Science in Computer Science.
Introduction CSE 1310 – Introduction to Computers and Programming Vassilis Athitsos University of Texas at Arlington 1.
Introduction CSE 1310 – Introduction to Computers and Programming Vassilis Athitsos University of Texas at Arlington 1.
 How Does This Make You Feel?.   Questions:  1 word that describes your item.  How is your item “viewed in public”  What would you change about.
C# Tutorial -1 ASP.NET Web Application with Visual Studio 2005.
B.A. (English Language) UNIVERSITI PUTRA MALAYSIA Second Semester 2011/2012 BBI 3211 (English for Specific Purposes)
Different approaches an analysis might use when investigating a system including: – Questionnaires – Interviews – Document gathering and analysis.
How to write a professional paper. 1. Developing a concept of the paper 2. Preparing an outline 3. Writing the first draft 4. Topping and tailing 5. Publishing.
So you look like the sort of person who knows about webs... Yip So what's a web page? It's just a page of information, on the world wide web, that people.
The Technical Report Hitting the ground running. Research Research is a way of… What are some everyday uses of research? What experiences have you had.
UoS Libraries 2011 EndNote X5 - basic graduate session.
Corpus-based evaluation of Referring Expression Generation Albert Gatt Ielka van der Sluis Kees van Deemter Department of Computing Science University.
Jette Viethen 20 April 2007NLGeval07 Automatic Evaluation of Referring Expression Generation is Possible.
UWMS Data Mining Workshop Content Analysis: Automated Summarizing Prof. Marti Hearst SIMS 202, Lecture 16.
DeepDive Model Dongfang Xu Ph.D student, School of Information, University of Arizona Dec 13, 2015.
Copyright © 2016 by Pearson Education, Inc. All rights reserved. Richard Johnson-Sheehan PURDUE UNIVERSITY Charles Paine UNIVERSITY OF NEW MEXICO Chapter.
C HU H AI C OLLEGE O F H IGHER E DUCATION D EPARTMENT O F C OMPUTER S CIENCE Preparation of Final Year Project Report Bachelor of Science in Computer Science.
Introduction CSE 1310 – Introduction to Computers and Programming Vassilis Athitsos University of Texas at Arlington 1.
SAGE TESTING HELPFUL HINTS Bring your ear buds if you have them. You’ll like yours better than ours. EVERYONE will have the test read to them (by the computer,
Software Engineering, COMP201 Slide 1 Software Requirements BY M D ACHARYA Dept of Computer Science.
Funded by the Library of Congress.
What Skills Help You Analyze Functional Documents? Feature Menu Analyzing Structure and Format Finding the Main Idea Taking Notes Comparing and Contrasting.
Finding, Reading, & Citing Scientific Papers. Types of scientific literature? Primary literature ~ current, specialized, with data research articles,
Exercise 1 Content –Covers chapters 1-4 Chapter 1 (read) Chapter 2 (important for the exercise, 2.6 comes later) Chapter 3 (especially 3.1, 3.2, 3.5) Chapter.
Individuals who are interested in using microsoft ebook word templates can find these sources online. Ebook templates can make writing of ebooks easier.
1 CS 430 / INFO 430: Information Retrieval Lecture 20 Web Search 2.
Harnessing the Deep Web : Present and Future -Tushar Mhaskar Jayant Madhavan, Loredana Afanasiev, Lyublena Antova, Alon Halevy January 7,
Objectives of the Course and Preliminaries
Software Documentation
DAY 2: Create PT: Make a Plan
Principles of report writing
Delayed Evaluation Special forms in Scheme (e.g., if and cond) do not use applicative order evaluation Only one of two or more expressions is actually.
Text Structure English 7 & 8.
Text Structure English 7 & 8.
Mini Extended Essay 1st Draft Peer Review.
Kees van Deemter Computing Science University of Aberdeen
Presentation transcript:

Kees van Deemter Generation of Referring Expressions: a crash course Background information and Project HIT 2010

1. Background Information A survey paper (draft!) on Generation of Referring Expressions, which I’m writing with Emiel Krahmer (University of Tilburg). Go to the course web page: bin-2010/ bin-2010/ then click on Survey (draft, in pdf format) Particularly relevant for you: Sections 1,2,5.

2. Project:Describing objects in a Knowledge Base

After the lecture and some reading, you will know about reference To refer to an object is to identify it GRE algorithms produce descriptions that refer in this strict sense In daily life, it is often important not just to identify an object, but to say what’s special about it Example: Given a database of digital cameras, where one camera is highlighted, describe this camera.

Example 1 Price Resol Weight Nikon 300p 20mp 660gr Canon 200p 11mp 650gr Kodak 50p 6mp 670gr Identifying the Nikon is easy, e.g. “660gr” But “660gr” is less useful than “300p”, or “most expensive”, or “most expensive, highest resolution”

PROJECT 1: Describing individual items Choose a domain of products and a KB that contains products of this kind (e.g., digital cameras, chosen from an existing web page) Construct an NLG program that can describe any given item in the KB, in such a way that it is likely to be useful to a customer Invent an evaluation procedure for your algorithm. Purpose: test the usefulness of the descriptions generated

PROJECT 1 Your program should work on any KB that has the required format – But some objects may be difficult to describe in a useful way (e.g., if some other objects are very similar to the highlighted object) I want you to focus on content determination (i.e., choice of properties is more important than choice of words) I don’t expect you to have time to actually perform the evaluation

PROJECT 2: Compare & Contrast Similar to PROJECT 1, but Given a KB with m entities in it, and 0≤n≤m of these m entities are highlighted: compare and contrast these n Special cases to watch out for: n=1 n=m

Example 2 Price Resol Weight Nikon 300p 20mp 660gr Canon 200p 11mp 650gr Kodak 50p 6mp 670gr In English: “These are the two most expensive cameras in this KB. Of these two, the Nikon has the highest resolution.” Focussing on content: Common: most expensive Contrast: Resol(Nikon) > Resol(Canon)

Your report should contain What types of inputs your program accepts A description of your algorithm Examples of output texts (+ the inputs from which they were generated) Discussion of pros and cons of your approach – What would you do differently next time? – What would you do next if you had time? Installation & usual manuals for your program

Summing up This project comes in two different flavours In each case, you’ll be looking at a possible generalisation of GRE: – Project 1: Descriptions that do more (and probably less!) than identification – Project 2: Compare & Contrast Questions, or alternative ideas? Let me know!