Named Entity Recognition. Natural Language Processing Emory University Jinho D. Choi
|
|
|
- Clinton Crawford
- 6 years ago
- Views:
Transcription
1 Named Entity Recognition Natural Language Processing Emory University Jinho D. Choi
2 Named Entity Recognition 2
3 Named Entity Recognition Classify the named entity tag of each chunk. 2
4 Named Entity Recognition Classify the named entity tag of each chunk. 2
5 Named Entity Recognition Peson Classify the named entity tag of each chunk. 2
6 Named Entity Recognition Classify the named entity tag of each chunk. Peson Organization 2
7 Named Entity Recognition Classify the named entity tag of each chunk. Peson Organization Location 2
8 Named Entity Recognition Classify the named entity tag of each chunk. Peson Organization Location A chunk can be decomposed into a sequence of tokens. 2
9 Named Entity Recognition Classify the named entity tag of each chunk. Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC A chunk can be decomposed into a sequence of tokens. 2
10 Named Entity Recognition Classify the named entity tag of each chunk. Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC A chunk can be decomposed into a sequence of tokens. Classify the named entity tag of each token. 2
11 Named Entity Recognition Classify the named entity tag of each chunk. Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC A chunk can be decomposed into a sequence of tokens. Classify the named entity tag of each token. Different from part-of-speech tagging? 2
12 BIO Notation Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC 3
13 BIO Notation Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC Semantic overload Semantic overload 3
14 BIO Notation Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC Semantic overload Semantic overload B: Beginning I: Inside O: Outside 3
15 BIO Notation Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC Semantic overload Semantic overload B-PER B-ORG I-ORG B-LOC I-LOC... B: Beginning I: Inside O: Outside 3
16 BIO Notation Peson Organization Location PER O O O O ORG ORG O O LOC LOC LOC LOC Semantic overload Semantic overload B-PER B-ORG I-ORG B-LOC I-LOC... B: Beginning I: Inside O: Outside Still not enough? 3
17 BILOU Notation B: Beginning I: Inside O: Outside 4
18 BILOU Notation B: Beginning I: Inside O: Outside L: Last U: Unit 4
19 BILOU Notation B: Beginning I: Inside O: Outside L: Last U: Unit Jinho Emory University United States of America 4
20 BILOU Notation B: Beginning I: Inside O: Outside L: Last U: Unit Jinho Emory University United States of America B-PER B-ORG I-ORG B-LOC I-LOC I-LOC I-LOC 4
21 BILOU Notation B: Beginning I: Inside O: Outside L: Last U: Unit Jinho Emory University United B-PER B-ORG I-ORG B-LOC U-PER B-ORG L-ORG B-LOC States I-LOC I-LOC of I-LOC I-LOC America I-LOC L-LOC 4
22 BILOU Notation B: Beginning I: Inside O: Outside L: Last U: Unit Jinho Emory University United B-PER B-ORG I-ORG B-LOC U-PER B-ORG L-ORG B-LOC States I-LOC I-LOC of I-LOC I-LOC America I-LOC L-LOC 4
23 Features DBPedia: 5
24 Features Similar to part-of-speech tagging. DBPedia: 5
25 Features Similar to part-of-speech tagging. Features from knowledge-base. DBPedia: 5
26 Features Similar to part-of-speech tagging. Features from knowledge-base. Freebase: DBPedia: 5
27 Features Similar to part-of-speech tagging. Features from knowledge-base. Freebase: DBPedia: DBPedia Spotlight 5
28 Clustering Features 6
29 Clustering Features Given a large corpus, construct word clusters. 6
30 Clustering Features Given a large corpus, construct word clusters. Brown cluster 6
31 Clustering Features Given a large corpus, construct word clusters. Brown cluster day year week month quarter half ii accounts people customers individuals employees students ] il I 6
32 Clustering Features Given a large corpus, construct word clusters. Brown cluster day year week month quarter half ii accounts people customers individuals employees students ] il I Use the cluster info as an extra feature for each token. 6
33 Evaluation 7
34 Evaluation 7
35 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold 7
36 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold System U-P O O O O U-R U-R O O B-L I-L L-L 0 7
37 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold System U-P O O O O U-R U-R O O B-L I-L L-L 0 7
38 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold System U-P O O O O U-R U-R O O B-L I-L L-L 0 7
39 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold System U-P O O O O U-R U-R O O B-L I-L L-L 0 Exact match 7
40 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold System U-P O O O O U-R U-R O O B-L I-L L-L 0 Precision Exact match Recall p = correct entities predicted entities = 1 4 r = correct entities true entities = 1 3 7
41 Evaluation U-P O O O O B-R L-R O O B-L I-L I-L L-L Gold System U-P O O O O U-R U-R O O B-L I-L L-L 0 Precision Exact match Recall p = correct entities predicted entities = 1 4 r = correct entities true entities = 1 3 F 1=2 p r p + r 7
Extracting Social Networks from Literary Fiction
Extracting Social Networks from Literary Fiction David K. Elson, Nicholas Dames, Kathleen R. McKeown Presented by Audrey Lawrence and Kathryn Lingel Introduction Network of 19th century novel's social
Taxonomic Name Recognition (TNR) in Biodiversity Heritage
Taxonomic Name Recognition (TNR) in Biodiversity Heritage Library L L Qin Wei, Chris Freeland, P. Bryan Heidorn Missouri Botanical Garden Co-author Chris Freeland Director of Biodiversity Heritage Library
Evaluation. Fabian M. Suchanek
Evaluation Fabian M. Suchanek 53 Semantic IE Reasoning Fact Extraction You are here Instance Extraction singer Entity Disambiguation singer Elvis Entity Recognition Source Selection and Preparation Detect
DISCIPLINARY AND INTERDISCIPLINARY RESEARCH AT NSF
DISCIPLINARY AND INTERDISCIPLINARY RESEARCH AT NSF Myron Gutmann Leah Nichols COSSA Colloquium 2012 November 2012 1 ACKNOWLEDGEMENTS Dave Newman, University of California, Irvine Julia Lane, American Institutes
Building a Business Knowledge Base by a Supervised Learning and Rule-Based Method
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS VOL. 9, NO. 1, Jan. 2015 407 Copyright 2015 KSII Building a Business Knowledge Base by a Supervised Learning and Rule-Based Method Sungho Shin 1, 2,
Introduction to Markov Models
Introduction to Markov Models But first: A few preliminaries Estimating the probability of phrases of words, sentences, etc. CIS 391 - Intro to AI 2 What counts as a word? A tricky question. How to find
n r for the number. (n r)!r!
Throughout we use both the notations ( ) n r and C n n! r for the number (n r)!r! 1 Ten points are distributed around a circle How many triangles have all three of their vertices in this 10-element set?
Unit 6 - Number Games and Crayon Puzzles Unit 8 - Twos, Fives, and Tens Unit 7 - Color, Shape, and Size. Unit 9 - Blocks and Boxes.
GRADE 1 Pacing 2010-2011 Unit 1 - How Many of Each? Unit 2 - Making Shapes and Designing Quilts Unit 3 - Solving Story Problems Unit 4 - What Would You Rather Be? Unit 5 - Fish Lengths and Animal Jumps
Oct-09 Nov-09 Dec-09. Jan-10 Feb-10 Mar-10. Apr-10 May-10 Jun-10
Grade 1 Pacing 2009-2010 Investigations 2009 Investigations How Many of Each? Number Games and Crayon Puzzles S M T W T F S Making Shapes and Designing Quilts Twos, Fives, and Tens 1 2 3 4 5 Solving Story
The Third International Chinese Language Processing Bakeoff: Word Segmentation and Named Entity Recognition
The Third International Chinese Language Processing Bakeoff: Word Segmentation and Named Entity Recognition Gina-Anne Levow University of Chicago 1100 E. 58th St. Chicago, IL 60637 USA levow@cs.uchicago.edu
Lesson 11: Linear and Exponential Investigations
Hart Interactive Algebra Lesson Lesson : Linear and Exponential Investigations Opening Exercise In this lesson, you ll be exploring linear and exponential function in five different investigations. You
11/13/18. Introduction to RNNs for NLP. About Me. Overview SHANG GAO
Introduction to RNNs for NLP SHANG GAO About Me PhD student in the Data Science and Engineering program Took Deep Learning last year Work in the Biomedical Sciences, Engineering, and Computing group at
Simple Large-scale Relation Extraction from Unstructured Text
Simple Large-scale Relation Extraction from Unstructured Text Christos Christodoulopoulos and Arpit Mittal Amazon Research Cambridge Alexa Question Answering Alexa, what books did Carrie Fisher write?
SOFT 437. Software Performance Analysis. What is UML? UML Tutorial
SOFT 437 Software Performance Analysis UML Tutorial What is UML? Unified Modeling Language (UML) is a standard language for specifying, visualizing, constructing, and documenting the artifacts for software
Applying Text Analytics to the Patent Literature to Gain Competitive Insight
Applying Text Analytics to the Patent Literature to Gain Competitive Insight Gilles Montier, Strategic Account Manager, Life Sciences TEMIS, Paris www.temis.com Lessons Learnt TEMIS has been working with
신경망기반자동번역기술. Konkuk University Computational Intelligence Lab. 김강일
신경망기반자동번역기술 Konkuk University Computational Intelligence Lab. http://ci.konkuk.ac.kr kikim01@kunkuk.ac.kr 김강일 Index Issues in AI and Deep Learning Overview of Machine Translation Advanced Techniques in
MFL and Numeracy. Teachers of MFL in KS2 and KS3 reinforce:
MFL and Numeracy "When evaluating the achievement of pupils, inspectors consider...how well pupils develop a range of skills, including reading, writing, communication and mathematical skills, and how
PLEASE READ THIS INTRODUCTORY PAGE BEFORE YOU PROCEED FURTHER!!
SETTING UP LUMP SUM AND VACANT POSITIONS IN POSITION BUDGETING PLEASE READ THIS INTRODUCTORY PAGE BEFORE YOU PROCEED FURTHER!! Vacant positions, of which there are basically three types, are added to the
Curriculum Correlation Number Cluster 5: Composing and Decomposing
Master 43a Cluster 5: Composing and Decomposing ON 15.8: explore different Canadian coins, using coin manipulatives (e.g., role-play the purchasing of items at the store in the dramatic play area; determine
Neural Architectures for Named Entity Recognition
Neural Architectures for Named Entity Recognition Presented by Allan June 16, 2017 Slides: http://www.statnlp.org/event/naner.html Some content is taken from the original slides. Named Entity Recognition
Shimmer Braid. Month 3
Shimmer Braid Month 3 Make 4 Braids with purple points. Make 8 Braids with white points. Block Size 5 x 17 = Finished Block Size. Finished means after it is sewn into the quilt. 5 ½ x 17 ½ square = Unfinished
Curriculum Correlation Number Cluster 6: Early Place Value
Master 56a Cluster 6: Early Place Value ON 15.1 investigate (e.g., using a number line, a hundreds carpet, a board game with numbered squares) the idea that a number s position in the counting sequence
Midterm 2 Practice Problems
Midterm 2 Practice Problems May 13, 2012 Note that these questions are not intended to form a practice exam. They don t necessarily cover all of the material, or weight the material as I would. They are
Novel Error Recovery Architecture Based on Machine Learning
Novel Error Recovery Architecture Based on Machine Learning Cloud Zeng LITEON/Storage/NVM Lab Flash Memory Summit 2018 Santa Clara, CA 1 Error Recovery Flow Probability Density (Error Bits) FER (Frame
Attacking Quality Limitations:
Attacking Quality Limitations: New Approaches to Translation Technologies Hans Uszkoreit German Research Center for Artifical Intelligence (DFKI) and Saarland University Coordinator META-NET My Background
Third Grade: Mathematics. Unit 1: Math Strategies
Third Grade: Mathematics Unit 1: Math Strategies Math Strategies for Addition Open Number Line (Adding Up) The example below shows 543 + 387 using the open number line. First, you need to draw a blank
Part of Speech Tagging & Hidden Markov Models (Part 1) Mitch Marcus CIS 421/521
Part of Speech Tagging & Hidden Markov Models (Part 1) Mitch Marcus CIS 421/521 NLP Task I Determining Part of Speech Tags Given a text, assign each token its correct part of speech (POS) tag, given its
How to Help Your Child With Mathematics Calculations in KS2
How to Help Your Child With Mathematics Calculations in KS2 Getting Involved As well as the calculations we are looking at tonight, you can help your child by including maths in the conversations you have
Math Kindergarten. Within 10 Within 20 standard order, pairing each object with only one number name, and one name with one number of objects counted.
Math Kindergarten Reporting Categories - Kindergarten Number Sense Counting Identifying number of objects Writing numbers Comparing numbers Instant recognition of quantities (to 6) Counting on Standards
Introduction to Telecommunications and Computer Engineering Unit 3: Communications Systems & Signals
Introduction to Telecommunications and Computer Engineering Unit 3: Communications Systems & Signals Syedur Rahman Lecturer, CSE Department North South University syedur.rahman@wolfson.oxon.org Acknowledgements
Potential and Limitations of Commercial Sentiment Detection Tools
Potential and Limitations of Commercial Sentiment Detection Tools Fatih Uzdilli joint work with Mark Cieliebak and Oliver Dürr 03.12.2013 @ ESSEM 13 About Me Fatih Uzdilli Institute of Applied Information
A review of Reasoning About Rational Agents by Michael Wooldridge, MIT Press Gordon Beavers and Henry Hexmoor
A review of Reasoning About Rational Agents by Michael Wooldridge, MIT Press 2000 Gordon Beavers and Henry Hexmoor Reasoning About Rational Agents is concerned with developing practical reasoning (as contrasted
Counting Money. Counting. Money. Bridging the Employment Gap 2008 Retail 75
Counting Money Bridging the Employment Gap 2008 Retail 75 Bridging the Employment Gap 2008 Retail 76 Counting Money This unit will offer students a variety of strategies for counting dollars and cents,
PackPlay: Mining semantic data in collaborative games
PackPlay: Mining semantic data in collaborative games Nathan Green NC State University 890 Oval Drive Raleigh, NC 27695 Paul Breimyer NC State University 890 Oval Drive Raleigh, NC 27695 Vinay Kumar NC
VQ Source Models: Perceptual & Phase Issues
VQ Source Models: Perceptual & Phase Issues Dan Ellis & Ron Weiss Laboratory for Recognition and Organization of Speech and Audio Dept. Electrical Eng., Columbia Univ., NY USA {dpwe,ronw}@ee.columbia.edu
Image Analysis & Searching
Image Analysis & Searching 1 Searching Photos Look for photos like this one: Look for beach photos Look for photos taken Sept. 15, 2000 Look for photos with: Look for photos with Aunt Thelma 2 Annotating
Counting and Cardinality (CC)
Counting Cardinality (CC) K.CC.B Count to tell the number of objects. K.CC.A Know number names the counting sequence. Domain Cluster Stards 1 st nd rd 4 th K.CC.A.1 Count to 100 by ones, fives by tens.
SimSE Player s Manual
SimSE Player s Manual 1. Beginning a Game When you start a new game, you will see a window pop up that contains a short narrative about the game you are about to play. It is IMPERATIVE that you read this
Speech Processing. Simon King University of Edinburgh. additional lecture slides for
Speech Processing Simon King University of Edinburgh additional lecture slides for 2018-19 assignment Q&A writing exercise Roadmap Modules 1-2: The basics Modules 3-5: Speech synthesis Modules 6-9: Speech
Speaker Isolation in a Cocktail-Party Setting
Speaker Isolation in a Cocktail-Party Setting M.K. Alisdairi Columbia University M.S. Candidate Electrical Engineering Spring Abstract the human auditory system is capable of performing many interesting
V.S.B. ENGINEERING COLLEGE, KARUR. Department of Computer Science and Engineering
V.S.B. ENGINEERING COLLEGE, KARUR. Department of and Details of Faculty Paper Publications in National and International Journals Academic Year : 2016-2017 International Journals : Sl. Name of the Title
EARIN Jarosław Arabas Room #223, Electronics Bldg.
EARIN http://elektron.elka.pw.edu.pl/~jarabas/earin.html Jarosław Arabas jarabas@elka.pw.edu.pl Room #223, Electronics Bldg. Paweł Cichosz pcichosz@elka.pw.edu.pl Room #215, Electronics Bldg. EARIN Jarosław
Wildlife Census via LSH-based animal tracking APOORV PATWARDHAN
1 Wildlife Census via LSH-based animal tracking APOORV PATWARDHAN National Parks and wildlife conservation 2 Jim Corbett National Park, India Amboseli National Park, Kenya And many more The Challenge 3
Forecasting Technology Emergence from Metadata and Language of Scientific Publications and Patents 1
Forecasting Technology Emergence from Metadata and Language of Scientific Publications and Patents 1 Olga Babko-Malaya, Andy Seidel, Daniel Hunter, Jason HandUber, Michelle Torrelli and Fotis Barlos {olga.babko-malaya,
Multiplying and Dividing Integers
Multiplying and Dividing Integers Some Notes on Notation You have been writing integers with raised signs to avoid confusion with the symbols for addition and subtraction. However, most computer software
Image Analysis ECSS projects update
Image Analysis ECSS projects update Decomposing Bodies (PI A. Langmead (Univ of Pittsburgh): ~20K early 20 th century Bertillon prison id cards analyzing, digitizing and re-presenting the data examine
Revised Elko County School District 2 nd Grade Math Learning Targets
Elko County School District 2 nd Grade Math Learning Targets Content Standard 1.0 Students will accurately calculate and use estimation techniques, number relationships, operation rules, and algorithms;
Relation Extraction, Neural Network, and Matrix Factorization
Relation Extraction, Neural Network, and Matrix Factorization Presenter: Haw-Shiuan Chang UMass CS585 guest lecture on 2016 Nov. 17 Most slides prepared by Patrick Verga Relation Extraction Knowledge Graph
Value-added Applications with Deep Learning. src:
SMART TOURISM Value-added Applications with Deep Learning src: https://www.wttc.org/-/media/files/reports/economic-impact-research/countries-2017/thailand2017.pdf Somnuk Phon-Amnuaisuk, Minh-Son Dao, CIE,
Math 36 "Fall 08" 5.2 "Sum and Di erence Identities" * Find exact values of functions of rational multiples of by using sum and di erence identities.
Math 36 "Fall 08" 5.2 "Sum and Di erence Identities" Skills Objectives: * Find exact values of functions of rational multiples of by using sum and di erence identities. * Develop new identities from the
Participant Identification in Haptic Systems Using Hidden Markov Models
HAVE 25 IEEE International Workshop on Haptic Audio Visual Environments and their Applications Ottawa, Ontario, Canada, 1-2 October 25 Participant Identification in Haptic Systems Using Hidden Markov Models
Fact Harvesting from Natural Language Text in Wikipedia
Fact Harvesting from Natural Language Text in Wikipedia Matteo Cannaviccio (Roma Tre University) Denilson Barbosa (University of Alberta) Paolo Merialdo (Roma Tre University) July 6, 2016 AT&T Knowledge
Sketching Interface. Larry Rudolph April 24, Pervasive Computing MIT SMA 5508 Spring 2006 Larry Rudolph
Sketching Interface Larry April 24, 2006 1 Motivation Natural Interface touch screens + more Mass-market of h/w devices available Still lack of s/w & applications for it Similar and different from speech
Lesson 27: Sine and Cosine of Complementary and Special Angles
Lesson 7 M Classwork Example 1 If α and β are the measurements of complementary angles, then we are going to show that sin α = cos β. In right triangle ABC, the measurement of acute angle A is denoted
Sketching Interface. Motivation
Sketching Interface Larry Rudolph April 5, 2007 1 1 Natural Interface Motivation touch screens + more Mass-market of h/w devices available Still lack of s/w & applications for it Similar and different
Spatialization and Timbre for Effective Auditory Graphing
18 Proceedings o1't11e 8th WSEAS Int. Conf. on Acoustics & Music: Theory & Applications, Vancouver, Canada. June 19-21, 2007 Spatialization and Timbre for Effective Auditory Graphing HONG JUN SONG and
Patent Analysis for Organization based on Patent Evolution Model
Patent for Organization based on Patent Evolution Model Yunji Jang, UST Technology nformation, University of Science and Technology, UST yunji@kisti.re.kr Do-Heon Jung Technology nformation, heon@kisti.re.kr
Second Quarter Benchmark Expectations for Units 3 and 4
Mastery Expectations For the Fourth Grade Curriculum In Fourth Grade, Everyday Mathematics focuses on procedures, concepts, and s in three critical areas: Understanding and fluency with multi-digit multiplication,
Wavelet Packets Best Tree 4 Points Encoded (BTE) Features
Wavelet Packets Best Tree 4 Points Encoded (BTE) Features Amr M. Gody 1 Fayoum University Abstract The research aimed to introduce newly designed features for speech signal. The newly developed features
An Example Cognitive Architecture: EPIC
An Example Cognitive Architecture: EPIC David E. Kieras Collaborator on EPIC: David E. Meyer University of Michigan EPIC Development Sponsored by the Cognitive Science Program Office of Naval Research
Deep Learning for Broad Coverage Semantics: SRL, Coreference, and Beyond
Deep Learning for Broad Coverage Semantics: SRL, Coreference, and Beyond Luke Zettlemoyer * Joint work with Luheng He, Kenton Lee, Matthew Peters*, Christopher Clark, Matthew Gardner*, Mohit Iyyer*, Mandar
Towards the definition of a Science Base for Enterprise Interoperability: A European Perspective
Towards the definition of a Science Base for Enterprise Interoperability: A European Perspective Keith Popplewell Future Manufacturing Applied Research Centre, Coventry University Coventry, CV1 5FB, United
Information Extraction. CS6200 Information Retrieval (and a sort of advertisement for NLP in the spring)
Information Extraction CS6200 Information Retrieval (and a sort of advertisement for NLP in the spring) 1 Informa(on Extrac(on Automa(cally extract structure from text annotate document using tags to iden(fy
Common Core State Standard for Mathematics
Domain: Counting and Cardinality Cluster: Know number names and the count sequence 1. Count to 100 by ones and by tens. CC.K.CC.1 2. Count forward beginning from a given number within the known sequence
Vocabulary Cards and Word Walls Revised: May 23, 2011
Vocabulary Cards and Word Walls Revised: May 23, 2011 Important Notes for Teachers: The vocabulary cards in this file match the Common Core, the math curriculum adopted by the Utah State Board of Education,
An affective intelligent driving agent: driver's trajectory and activities prediction.
An affective intelligent driving agent: driver's trajectory and activities prediction. The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters.
Bow Tie Cigar Company PR Plan
Bow Tie Cigar Company PR Plan Logan Fox Chelsea Sullivan Sidney Rehg Kelci Jones Index Situation Analysis Company Bio Objectives, Strategies and Tactics Objectives Strategies Tactics Increase Publication
NEURAL TEXT GENERATION IN STORIES USING ENTITY REPRESENTATIONS
1 / 17 NEURAL TEXT GENERATION IN STORIES USING ENTITY REPRESENTATIONS AS CONTEXT Elizabeth Clark Yangfeng Ji Noah A. Smith Paul G. Allen School of Computer Science & Engineering University of Washington
Algebra Adventure Directions. Format: Individual or Pairs (works best)
Algebra Adventure Directions Format: Individual or Pairs (works best) Directions: Each student will receive an Algebra Adventure WS that they will keep track of their stations and work. Each pair will
Environmental Sound Recognition using MP-based Features
Environmental Sound Recognition using MP-based Features Selina Chu, Shri Narayanan *, and C.-C. Jay Kuo * Speech Analysis and Interpretation Lab Signal & Image Processing Institute Department of Computer
Objective: Classify shapes based on defining attributes using examples, variants, and non-examples. (10 minutes) (5 minutes)
Lesson 1 1 Lesson 1 Objective: Classify shapes based on defining attributes using examples, variants, Suggested Lesson Structure Fluency Practice Application Problem Concept Development Student Debrief
Service Robots in an Intelligent House
Service Robots in an Intelligent House Jesus Savage Bio-Robotics Laboratory biorobotics.fi-p.unam.mx School of Engineering Autonomous National University of Mexico UNAM 2017 OUTLINE Introduction A System
Appendices master s degree programme Human Machine Communication
Appendices master s degree programme Human Machine Communication 2015-2016 Appendix I Teaching outcomes of the degree programme (art. 1.3) 1. The master demonstrates knowledge, understanding and the ability
Key-Value Memory Networks for Directly Reading Documents (EMNLP16)
Key-Value Memory Networks for Directly Reading Documents (EMNLP16) Alexander H. Miller 1, Adam Fisch 1, Jesse Dodge 1,2, Amir-Hossein Karimi 1, Antoine Bordes 1, Jason Weston 1 1 Facebook AI Research 2
Bit Error Probability Computations for M-ary Quadrature Amplitude Modulation
KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY ELECTRICAL ENGINEERING DEPARTMENT Bit Error Probability Computations for M-ary Quadrature Amplitude Modulation Ronell B. Sicat ID: 4000217 Professor Tareq
7.4 Permutations and Combinations
7.4 Permutations and Combinations The multiplication principle discussed in the preceding section can be used to develop two additional counting devices that are extremely useful in more complicated counting
Comparing the Quality of 2010 Census Proxy Responses with Administrative Records
Comparing the Quality of 2010 Census Proxy Responses with Administrative Records Mary H. Mulry & Andrew Keller U.S. Census Bureau 2015 International Total Survey Error Conference September 22, 2015 Any
The Game-Theoretic Approach to Machine Learning and Adaptation
The Game-Theoretic Approach to Machine Learning and Adaptation Nicolò Cesa-Bianchi Università degli Studi di Milano Nicolò Cesa-Bianchi (Univ. di Milano) Game-Theoretic Approach 1 / 25 Machine Learning
Teacher s Notes. Problem of the Month: Courtney s Collection
Teacher s Notes Problem of the Month: Courtney s Collection Overview: In the Problem of the Month, Courtney s Collection, students use number theory, number operations, organized lists and counting methods
4.4: The Counting Rules
4.4: The Counting Rules The counting rules can be used to discover the number of possible for a sequence of events. Fundamental Counting Rule In a sequence of n events in which the first one has k 1 possibilities
Lesson 5: Area of Composite Shape Subject: Math Unit: Area Time needed: 60 minutes Grade: 6 th Date: 2 nd
Lesson 5: Area of Composite Shape Subject: Math Unit: Area Time needed: 60 minutes Grade: 6 th Date: 2 nd Materials, Texts Needed, or advanced preparation: Lap tops or computer with Geogebra if possible
Computing Scheme of Work Key Stage 1 Key Stage 2
Computing Scheme of Work 2017-2018 Key Stage 1 Key Stage 2 be exposed through everyday use of their 'high tech' and 'low tech' aids to fundamental principles and concepts of computer science, including
Mathematics Expectations Page 1 Grade 04
Mathematics Expectations Page 1 Problem Solving Mathematical Process Expectations 4m1 develop, select, and apply problem-solving strategies as they pose and solve problems and conduct investigations, to
Learning Structured Predictors
Learning Structured Predictors Xavier Carreras Xerox Research Centre Europe Supervised (Structured) Prediction Learning to predict: given training data { (x (1), y (1) ), (x (2), y (2) ),..., (x (m), y
SECTION SHOP DRAWINGS, PRODUCT DATA, AND SAMPLES
SECTION 01 33 23 - SHOP DRAWINGS, PRODUCT DATA, AND PART 1 - GENERAL 1.1 SUMMARY A. Products include, but are not limited to, the following construction submittals: 1. Shop Drawings. 2. Product Data. 3.
Introduction to HTK Toolkit
Introduction to HTK Toolkit Berlin Chen 2004 Reference: - Steve Young et al. The HTK Book. Version 3.2, 2002. Outline An Overview of HTK HTK Processing Stages Data Preparation Tools Training Tools Testing
Section 8.1. Sequences and Series
Section 8.1 Sequences and Series Sequences Definition A sequence is a list of numbers. Definition A sequence is a list of numbers. A sequence could be finite, such as: 1, 2, 3, 4 Definition A sequence
Data-driven HRI: Learning social behaviors by example from human-human interaction
Author Preprint. The final publication is available at http://ieeexplore.ieee.org/document/7539621/ P. Liu, D. F. Glas, T. Kanda, and H. Ishiguro, "Data-Driven HRI: Learning Social Behaviors by Example
Indiana K-12 Computer Science Standards
Indiana K-12 Computer Science Standards What is Computer Science? Computer science is the study of computers and algorithmic processes, including their principles, their hardware and software designs,
Semantic Localization of Indoor Places. Lukas Kuster
Semantic Localization of Indoor Places Lukas Kuster Motivation GPS for localization [7] 2 Motivation Indoor navigation [8] 3 Motivation Crowd sensing [9] 4 Motivation Targeted Advertisement [10] 5 Motivation
TITLE OF PRESENTATION. Elsevier s Challenge. Dynamic Knowledge Stores and Machine Translation. Presented By Marius Doornenbal,, Anna Tordai
Elsevier s Challenge Dynamic Knowledge Stores and Machine Translation Presented By Marius Doornenbal,, Anna Tordai Date 25-02-2016 OUTLINE Introduction Elsevier: from publisher to a data & analytics company
Local and Low-Cost White Space Detection
Local and Low-Cost White Space Detection Ahmed Saeed*, Khaled A. Harras, Ellen Zegura*, and Mostafa Ammar* *Georgia Institute of Technology Carnegie Mellon University Qatar White Space Definition A vacant
Combining Large Datasets of Patents and Trademarks
Combining Large Datasets of Patents and Trademarks Grid Thoma Computer Science Division, School of Science & Technology University of Camerino 14 th Italian STATA User Annual Meeting Florence, 16 Nov 2017
Software Engineering: A Practitioner s Approach, 7/e. Slides copyright 1996, 2001, 2005, 2009 by Roger S. Pressman
Chapter 9 Architectural Design Slide Set to accompany Software Engineering: A Practitioner s Approach, 7/e by Roger S. Pressman Slides copyright 1996, 2001, 2005, 2009 by Roger S. Pressman For non-profit
Machine-Learning Based Classification of Research Grant Award Records
Machine-Learning Based Classification of Research Grant Award Records Jeffrey Alexander, Ph.D. Christina Freyman, Ph.D. Center for Science, Technology & Economic Development John Byrnes, Ph.D. SRI Advanced
Fourth Grade Quarter 3 Unit 5: Fraction Equivalence, Ordering, and Operations Part 2, Topics F-H Approximately 14 days Begin around January 9 th
HIGLEY UNIFIED SCHOOL DISTRICT 2016/2017 INSTRUCTIONAL ALIGNMENT Fourth Grade Quarter 3 Unit 5: Fraction Equivalence, Ordering, and Operations Part 2, Topics F-H Approximately 14 days Begin around January
SpotTheLink: A Game for Ontology Alignment
SpotTheLink: A Game for Ontology Alignment Stefan Thaler, Elena Simperl, Katharina Siorpaes STI Innsbruck University of Innsbruck Austria stefan.thaler@sti2.at katharina.siorpaes@sti2.at AIFB Karlsruhe
Context-sensitive speech recognition for human-robot interaction
Context-sensitive speech recognition for human-robot interaction Pierre Lison Cognitive Systems @ Language Technology Lab German Research Centre for Artificial Intelligence (DFKI GmbH) Saarbrücken, Germany.
CS 7643: Deep Learning
CS 7643: Deep Learning Topics: Toeplitz matrices and convolutions = matrix-mult Dilated/a-trous convolutions Backprop in conv layers Transposed convolutions Dhruv Batra Georgia Tech HW1 extension 09/22
Kindergarten Mathematics Scope and Sequence
Kindergarten Mathematics Scope and Sequence Quarter 1 Domain Counting and Cardinality Geometry Standard K.CC.1 Count to 100 by ones and by tens. K.CC.2 Count forward within 100 beginning from any given