ADAPTIVE ROBUSTNESS ANALYSIS
|
|
- Blake McCarthy
- 5 years ago
- Views:
Transcription
1 ROBUSTNESS ANALYSIS 入力 ADAPTIVE OF 中文 Mike Tian-Jian Jiang, Cheng-Wei Lee, Chad Liu, Yung-Chun Chang, Wen-Lian Hsu Institute of Information Science, Academia Sinica
2 入力, Input Method (IM) Text Entry IIS, Sinica 2/30
3 groups/cue/mobileinteraction/ IIS, Sinica 3/30
4 Radical vs. Phonetic Homographs vs. Homophones IIS, Sinica 4/30
5 Disambiguation To predict or not IIS, Sinica 5/30
6 HCI, NLP (, SE) Unified error metrics (Soukoreff and MacKenzie, 2001) Error correction (Arif and Stuerzlinger, 2010) Reused vocabulary (Tanaka-Ishii et al., 2003) Backward compatibility (Suzuki and Gao, 2005) IIS, Sinica 6/30
7 Prediction and spell correction can be very annoying if they are not smart enough. For many applications, user input can be very noisy (imagine voice recognition or typing on a small screen), so the input methods must be robust against such noise. Finally, there is no standard data set or evaluation metric, which is necessary for quantitative analysis of user input experience. WTIM 2011 statements of call for papers IIS, Sinica 7/30
8 Prediction & Adaptation Properties of Chinese Phonetic IM IIS, Sinica 8/30
9 Adaptation via Online Implicit User Feedback (Online Offline Implicit Explicit) user feedback Adaptation procedure extends Tanaka-Ishii et al. (2003) User ambiguous source keystroke string s IM retrieve(s D) candidate chunks c[]; D {db profile} IM sort(c[]) IM compose(c[]) target string t eval(t) User modify(t) t IM adapt(t t) {feedback profile} IIS, Sinica 9/30
10 Dilemma Type long and (either right or wrong things) prosper IIS, Sinica 10/30
11 Amortized Cost Trade-off between benefic and cost of error correction IIS, Sinica 11/30
12 based on Unified Error Metrics Related to minimum string distance (MSD) error and key-stroke per character (KSPC) With Fitts law and Hick s law IIS, Sinica 12/30
13 Notations P: presented text T: transcribed text IS: input stream C: number of correct characters in T F: keystrokes for fixing in IS like editing, modifier, or navigation. INF: number of incorrect yet not fixed errors in T IF: number of incorrect but fixed errors (keystrokes in IS that are not F and not in T) IIS, Sinica 13/30
14 MSD(P,T ) S A 100% P: the quick brown fox T: the quixck brwn fox MSD(P, T) = 2 here Only for T without editing process IIS, Sinica 14/30
15 KSPC IS / T IIS, Sinica 15/30
16 Total Error Rate = MSD Error Rate = KSPC INF + IF C + INF + INF 100% INF C + INF 100% C + INF + IF + F C + INF T: the quixck brwn fox T : the quixck brown fox Total Error Rate(T ) = (2/18)% MSD Error Rate(T ) = (1/17)% KSPC(T ) = 19/17 IIS, Sinica 16/30
17 t F = a + blog 2 ( d w +1) t H = blog 2 (n +1) t: time a, b: empirical constants d: distance to target w: width of target n: number of equal possible choices Index of difficulty (ID): log 2 ((d/w) + 1) IIS, Sinica 17/30
18 Error Correction Conditions None, Forced, or Recommended conditions No relations between typing speed and correction attempt Spectrum of Recommended condition Situation Fixed characters INF IF F S 0 none INF S i some INF i IF i F i S all all 0 IF all F all IIS, Sinica 18/30
19 AC = Wasted Bandwidth Utilized Bandwidth = INF + IF + F C + INF + IF + F C C + INF + IF + F = INF + IF + F C INF 0 C AC i = INF i + IF i + F i C IF all C + F all C = INF 0 C + F all C penalty = t H INF 0 + t F max(d) C + INF 0 reward = C C + INF 0 AC modification = penalty reward = t INF H 0 + t F max(d) C MAC = INF 0 C + AC modification IIS, Sinica 19/30
20 Vocabulary Reuse % vocabulary reused only after a small offset window in KB (such that simulations of typing repeatedly are representative enough) IIS, Sinica 20/30
21 Backward Compatibility Error Ratio = errors by adaptation / corrections by adaptation IIS, Sinica 21/30
22 however, Error correction can be complicated. IIS, Sinica 22/30
23 Process of input Process of Correction Input [User doesn t correct] c γ correction [User corrects] [User doesn t verify] i γ verification [There are errors] [There are no errors] c, s error γ + γ c, h error [User verify] [There are no errors] [There are errors] i, s error γ + γ i, h error [User verify] [User doesn t verify] c γ verification [User doesn t correct] h correction s error [User corrects] i γ correction i verification h error = i γ correction + i, s i, h error + γ error c verification c, s γ error Correction ρ = γ + γ + γ ρ + ρ γ + + γ c correction c, h error
24 Simulation 3 IMs A, B, and C Phonetic method Bopomofo (Zhuyin) Daqian keyboard layout Data Academia Sinica Balanced Corpus 4,000 sentences 39,469 words Independent variables Context length k ρ h correction IIS, Sinica 24/30
25 Comparison of MAC IM-A seems to be different to others? IIS, Sinica 25/30
26 GBC at Context Length 6 Again, IM-A is segregated IIS, Sinica 26/30
27 more aspects wanted Than this V curve IIS, Sinica 27/30
28 Error Tolerance Level Futile Effort (E f ): never adapted chunks Beneficial Effort (E b ): adapted chunks Utility (U): before forgotten E b (IM-A) vs. E b (IM-B) his or her or its? 他 or 她 or 它 /ta1/ Correlation Coefficient to CAR E f avg E b avg U avg IM-A IM-B IIS, Sinica 28/30
29 How about a shared task? Just my humble suggestion :p IIS, Sinica 29/30
30 Thank YOU? Or do we have time for IIS, Sinica 30/30
31 Many MORE Things IIS, Sinica 31/30
32 zhi1- shi4 shi4- wei4 tou2- shi4 shi4- li4 dao4- shi4 shi4- shang4 fang1- shi4 shi4- gu4 chang2- shi4 shi4- yi2 yi4- shi4 shi4- ji1 zhi4- shi4 shi4- zhong1 IIS, Sinica 32/30
33 Reduced n-gram British Rail Enquiries P(Enquiries British, Rail) P(Enquiries Rail) IIS, Sinica 33/30
34 OpenVanilla IIS, Sinica 34/30
35 SearchTyping IIS, Sinica 35/30
36 Thank YOU! Any question or comment? IIS, Sinica 36/30
Control & Response Selection
Control & Response Selection Response Selection Response Execution 1 Types of control: Discrete Continuous Open-loop startle reaction touch typing hitting a baseball writing "motor programs" Closed-loop
More informationDeep Learning Basics Lecture 10: Neural Language Models. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 10: Neural Language Models Princeton University COS 495 Instructor: Yingyu Liang Natural language Processing (NLP) The processing of the human languages by computers One of
More informationUniversität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen. Language Models. Tobias Scheffer
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Language Models Tobias Scheffer Stochastic Language Models A stochastic language model is a probability distribution over words.
More informationA Hierarchical Representation for the Reference Database of On-Line Chinese Character Recognition
A Hierarchical Representation for the Reference Database of On-Line Chinese Character Recognition Ju-Wei Chen 1,2 and Suh-Yin Lee 1 1 Institute of Computer Science and Information Engineering National
More informationLanguage Models. CS6200: Information Retrieval. Slides by: Jesse Anderton
Language Models CS6200: Information Retrieval Slides by: Jesse Anderton What s wrong with VSMs? Vector Space Models work reasonably well, but have a few problems: They are based on bag-of-words, so they
More information[GMT31] THURSDAY 21 MAY
General Certificate of Secondary Education 2015 Mathematics Unit T3 Higher Tier [GMT31] THURSDAY 21 MAY 9.15 am 11.15 am MARK SCHEME 9466.01 F GCSE MATHEMATICS Introduction The mark scheme normally provides
More informationEmpirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs
Empirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs (based on slides by Sharon Goldwater and Philipp Koehn) 21 February 2018 Nathan Schneider ENLP Lecture 11 21
More information1.4 Mathematical Equivalence
1.4 Mathematical Equivalence Introduction a motivating example sentences that always have the same truth values can be used interchangeably the implied domain of a sentence In this section, the idea of
More informationChapter SBZJ I.1-2: Zhu za ming mu Text Translation Notes
Chapter 1 Shíbié Zájí: Section I 1.1 SBZJ I.1-2: Zhu za ming mu 1.1.1 Text 1.1 Tiān zhīyúrìyǔrìzhīyúxīn tóng. 1.2 Xīn zhīyúchuān yǔ chuān zhīyúdètóng. 2.1.1 Rìzhīxīn yū rìzhīyúshān tóng, 2.1.2 gǔ yǐshān
More informationISIS/Draw "Quick Start"
ISIS/Draw "Quick Start" Click to print, or click Drawing Molecules * Basic Strategy 5.1 * Drawing Structures with Template tools and template pages 5.2 * Drawing bonds and chains 5.3 * Drawing atoms 5.4
More informationUnsupervised Vocabulary Induction
Infant Language Acquisition Unsupervised Vocabulary Induction MIT (Saffran et al., 1997) 8 month-old babies exposed to stream of syllables Stream composed of synthetic words (pabikumalikiwabufa) After
More informationProbabilistic Language Modeling
Predicting String Probabilities Probabilistic Language Modeling Which string is more likely? (Which string is more grammatical?) Grill doctoral candidates. Regina Barzilay EECS Department MIT November
More informationCollaborative topic models: motivations cont
Collaborative topic models: motivations cont Two topics: machine learning social network analysis Two people: " boy Two articles: article A! girl article B Preferences: The boy likes A and B --- no problem.
More informationHomework 3 COMS 4705 Fall 2017 Prof. Kathleen McKeown
Homework 3 COMS 4705 Fall 017 Prof. Kathleen McKeown The assignment consists of a programming part and a written part. For the programming part, make sure you have set up the development environment as
More informationIssues on quantile autoregression
Issues on quantile autoregression Jianqing Fan and Yingying Fan We congratulate Koenker and Xiao on their interesting and important contribution to the quantile autoregression (QAR). The paper provides
More informationBuilding a Timeline Action Network for Evacuation in Disaster
Building a Timeline Action Network for Evacuation in Disaster The-Minh Nguyen, Takahiro Kawamura, Yasuyuki Tahara, and Akihiko Ohsuga Graduate School of Information Systems, University of Electro-Communications,
More informationPhysics 8 Monday, September 26, 2011
Physics 8 Monday, September 26, 2011 Midterm is canceled. There will be a Homework #3.5 instead. Homework #3 stops after problem 18. Problems 19 28 will move to Homework #3 1 2. Gradebook data (only your
More informationSemantics with Dense Vectors. Reference: D. Jurafsky and J. Martin, Speech and Language Processing
Semantics with Dense Vectors Reference: D. Jurafsky and J. Martin, Speech and Language Processing 1 Semantics with Dense Vectors We saw how to represent a word as a sparse vector with dimensions corresponding
More informationFan, Hai-fu Institute of Physics, Chinese Academy of Sciences, Beijing , China
Direct Methods in Crystallography Fan, Hai-fu Institute of Physics, Chinese Academy of Sciences, Beijing 100080, China An important branch of crystallography is the X-ray diffraction analysis of crystal
More informationCross-Lingual Language Modeling for Automatic Speech Recogntion
GBO Presentation Cross-Lingual Language Modeling for Automatic Speech Recogntion November 14, 2003 Woosung Kim woosung@cs.jhu.edu Center for Language and Speech Processing Dept. of Computer Science The
More informationUnit 8: Sequ. ential Circuits
CPSC 121: Models of Computation Unit 8: Sequ ential Circuits Based on slides by Patrice Be lleville and Steve Wolfman Pre-Class Learning Goals By the start of class, you s hould be able to Trace the operation
More informationThe Entropy of a Rapid Aimed Movement: Fitts Index of Difficulty versus Shannon s Entropy
Author manuscript, published in Proceedings of 3th IFIP TC 3 International Conference on Human Computer Interaction, Vol Part 4, pp. -39,. URL: http://dl.acm.org/citation.cfm?id=483.437 The Entropy of
More informationThe Workshop on Recent Progress in Theoretical and Computational Studies of 2D Materials Program
The Workshop on Recent Progress in Theoretical and Computational Program December 26-27, 2015 Beijing, China December 26-27, 2015, Beijing, China The Workshop on Recent Progress in Theoretical and Computational
More informationDeep Learning for Natural Language Processing. Sidharth Mudgal April 4, 2017
Deep Learning for Natural Language Processing Sidharth Mudgal April 4, 2017 Table of contents 1. Intro 2. Word Vectors 3. Word2Vec 4. Char Level Word Embeddings 5. Application: Entity Matching 6. Conclusion
More informationPart 1: You are given the following system of two equations: x + 2y = 16 3x 4y = 2
Solving Systems of Equations Algebraically Teacher Notes Comment: As students solve equations throughout this task, have them continue to explain each step using properties of operations or properties
More informationIntroduction to Pragmatics
Introduction to Pragmatics Summer 2016 Tuesdays 2:30--4:00pm @ 2321.HS 3H INSTRUCTOR Todor Koev (Todor.Koev@uni-duesseldorf.de) Presupposition projection Presupposition is a prevalent type of inference
More informationSciFinder Scholar Guide to Getting Started
SciFinder Scholar Guide to Getting Started What is SciFinder Scholar? SciFinder Scholar is the online version of Chemical Abstracts, covering chemistry publications worldwide from 1907 to the present.
More informationSamson Zhou. Pattern Matching over Noisy Data Streams
Samson Zhou Pattern Matching over Noisy Data Streams Finding Structure in Data Pattern Matching Finding all instances of a pattern within a string ABCD ABCAABCDAACAABCDBCABCDADDDEAEABCDA Knuth-Morris-Pratt
More informationLecture 2: Learning from Evaluative Feedback. or Bandit Problems
Lecture 2: Learning from Evaluative Feedback or Bandit Problems 1 Edward L. Thorndike (1874-1949) Puzzle Box 2 Learning by Trial-and-Error Law of Effect: Of several responses to the same situation, those
More informationA Study of the Steering Time Difference between Narrowing and Widening Circular Tunnels
116 A Study of the Steering Time Difference between Narrowing and Widening Circular Tunnels Shota Yamanaka Homei Miyashita The steering law is a robust model for expressing the relationship between movement
More informationLanguage Modeling. Introduction to N-grams. Many Slides are adapted from slides by Dan Jurafsky
Language Modeling Introduction to N-grams Many Slides are adapted from slides by Dan Jurafsky Probabilistic Language Models Today s goal: assign a probability to a sentence Why? Machine Translation: P(high
More informationNonlinear Controller Design of the Inverted Pendulum System based on Extended State Observer Limin Du, Fucheng Cao
International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 015) Nonlinear Controller Design of the Inverted Pendulum System based on Extended State Observer Limin Du,
More informationTuning as Linear Regression
Tuning as Linear Regression Marzieh Bazrafshan, Tagyoung Chung and Daniel Gildea Department of Computer Science University of Rochester Rochester, NY 14627 Abstract We propose a tuning method for statistical
More informationAgilent MassHunter Quantitative Data Analysis
Agilent MassHunter Quantitative Data Analysis Presenters: Howard Sanford Stephen Harnos MassHunter Quantitation: Batch Table, Compound Information Setup, Calibration Curve and Globals Settings 1 MassHunter
More informationChapter 3: Basics of Language Modelling
Chapter 3: Basics of Language Modelling Motivation Language Models are used in Speech Recognition Machine Translation Natural Language Generation Query completion For research and development: need a simple
More informationNatural Language Processing. Statistical Inference: n-grams
Natural Language Processing Statistical Inference: n-grams Updated 3/2009 Statistical Inference Statistical Inference consists of taking some data (generated in accordance with some unknown probability
More informationAdministration. CSCI567 Machine Learning (Fall 2018) Outline. Outline. HW5 is available, due on 11/18. Practice final will also be available soon.
Administration CSCI567 Machine Learning Fall 2018 Prof. Haipeng Luo U of Southern California Nov 7, 2018 HW5 is available, due on 11/18. Practice final will also be available soon. Remaining weeks: 11/14,
More informationTop Ten Algorithms Class 6
Top Ten Algorithms Class 6 John Burkardt Department of Scientific Computing Florida State University... http://people.sc.fsu.edu/ jburkardt/classes/tta 2015/class06.pdf 05 October 2015 1 / 24 Our Current
More informationLanguage Modeling. Introduction to N-grams. Many Slides are adapted from slides by Dan Jurafsky
Language Modeling Introduction to N-grams Many Slides are adapted from slides by Dan Jurafsky Probabilistic Language Models Today s goal: assign a probability to a sentence Why? Machine Translation: P(high
More informationMathematics Background
For a more robust teacher experience, please visit Teacher Place at mathdashboard.com/cmp3 Patterns of Change Through their work in Variables and Patterns, your students will learn that a variable is a
More informationPart A. P (w 1 )P (w 2 w 1 )P (w 3 w 1 w 2 ) P (w M w 1 w 2 w M 1 ) P (w 1 )P (w 2 w 1 )P (w 3 w 2 ) P (w M w M 1 )
Part A 1. A Markov chain is a discrete-time stochastic process, defined by a set of states, a set of transition probabilities (between states), and a set of initial state probabilities; the process proceeds
More information30. TRANSFORMING TOOL #1 (the Addition Property of Equality)
30 TRANSFORMING TOOL #1 (the Addition Property of Equality) sentences that look different, but always have the same truth values What can you DO to a sentence that will make it LOOK different, but not
More informationEvaluation on source rocks and the oil-source correlation in Bayanhushu sag of Hailaer Basin
30 2 2011 6 GLOBAL GEOLOGY Vol. 30 No. 2 Jun. 2011 1004-5589 2011 02-0231 - 07 163712 3 7 Ⅰ Ⅱ1 3 - - P618. 130 A doi 10. 3969 /j. issn. 1004-5589. 2011. 02. 011 Evaluation on source rocks and the oil-source
More informationSOLVING LINEAR INEQUALITIES
Topic 15: Solving linear inequalities 65 SOLVING LINEAR INEQUALITIES Lesson 15.1 Inequalities on the number line 15.1 OPENER Consider the inequality x > 7. 1. List five numbers that make the inequality
More informationFoundations of Natural Language Processing Lecture 5 More smoothing and the Noisy Channel Model
Foundations of Natural Language Processing Lecture 5 More smoothing and the Noisy Channel Model Alex Lascarides (Slides based on those from Alex Lascarides, Sharon Goldwater and Philipop Koehn) 30 January
More informationConditional Random Fields
Conditional Random Fields Micha Elsner February 14, 2013 2 Sums of logs Issue: computing α forward probabilities can undeflow Normally we d fix this using logs But α requires a sum of probabilities Not
More informationNgram Review. CS 136 Lecture 10 Language Modeling. Thanks to Dan Jurafsky for these slides. October13, 2017 Professor Meteer
+ Ngram Review October13, 2017 Professor Meteer CS 136 Lecture 10 Language Modeling Thanks to Dan Jurafsky for these slides + ASR components n Feature Extraction, MFCCs, start of Acoustic n HMMs, the Forward
More informationLecture PowerPoints. Chapter 1 Physics: Principles with Applications, 7 th edition Giancoli
Lecture PowerPoints Chapter 1 Physics: Principles with Applications, 7 th edition Giancoli This work is protected by United States copyright laws and is provided solely for the use of instructors in teaching
More informationFIT100 Spring 01. Project 2. Astrological Toys
FIT100 Spring 01 Project 2 Astrological Toys In this project you will write a series of Windows applications that look up and display astrological signs and dates. The applications that will make up the
More informationLet s now begin to formalize our analysis of sequential machines Powerful methods for designing machines for System control Pattern recognition Etc.
Finite State Machines Introduction Let s now begin to formalize our analysis of sequential machines Powerful methods for designing machines for System control Pattern recognition Etc. Such devices form
More informationSciFinder Scholar Guide to Getting Started
SciFinder Scholar Guide to Getting Started What is SciFinder Scholar? SciFinder Scholar is the online version of Chemical Abstracts, covering chemistry publications worldwide from 1907 to the present.
More informationPart I: Web Structure Mining Chapter 1: Information Retrieval and Web Search
Part I: Web Structure Mining Chapter : Information Retrieval an Web Search The Web Challenges Crawling the Web Inexing an Keywor Search Evaluating Search Quality Similarity Search The Web Challenges Tim
More informationCreation and modification of a geological model Program: Stratigraphy
Engineering manual No. 39 Updated: 11/2018 Creation and modification of a geological model Program: Stratigraphy File: Demo_manual_39.gsg Introduction The aim of this engineering manual is to explain the
More informationOptical Character Recognition of Jutakshars within Devanagari Script
Optical Character Recognition of Jutakshars within Devanagari Script Sheallika Singh Shreesh Ladha Supervised by : Dr. Harish Karnick, Dr. Amit Mitra UGP Presentation, 10 April 2016 OCR of Jutakshars within
More informationLinear classifiers: Overfitting and regularization
Linear classifiers: Overfitting and regularization Emily Fox University of Washington January 25, 2017 Logistic regression recap 1 . Thus far, we focused on decision boundaries Score(x i ) = w 0 h 0 (x
More information{ Jurafsky & Martin Ch. 6:! 6.6 incl.
N-grams Now Simple (Unsmoothed) N-grams Smoothing { Add-one Smoothing { Backo { Deleted Interpolation Reading: { Jurafsky & Martin Ch. 6:! 6.6 incl. 1 Word-prediction Applications Augmentative Communication
More informationL E A R N I N G E X P E R I E N C E
MARISA YAMADA ETEC 690 4.18.13 TALKING IS THE NEW TYPING - A P P L E C H A L L E N G I N G S M A R T P H O N E U S E R S T O D I C T AT E I N S T E A D O F T Y P E I N O R D E R T O E N R I C H T H E M
More informationPlease bring the task to your first physics lesson and hand it to the teacher.
Pre-enrolment task for 2014 entry Physics Why do I need to complete a pre-enrolment task? This bridging pack serves a number of purposes. It gives you practice in some of the important skills you will
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2010 Lecture 22: Nearest Neighbors, Kernels 4/18/2011 Pieter Abbeel UC Berkeley Slides adapted from Dan Klein Announcements On-going: contest (optional and FUN!)
More informationEngineering Part IIB: Module 4F11 Speech and Language Processing Lectures 4/5 : Speech Recognition Basics
Engineering Part IIB: Module 4F11 Speech and Language Processing Lectures 4/5 : Speech Recognition Basics Phil Woodland: pcw@eng.cam.ac.uk Lent 2013 Engineering Part IIB: Module 4F11 What is Speech Recognition?
More informationChapter 11: WinTDR Algorithms
Chapter 11: WinTDR Algorithms This chapter discusses the algorithms WinTDR uses to analyze waveforms including: Bulk Dielectric Constant; Soil Water Content; Electrical Conductivity; Calibrations for probe
More informationFrom perceptrons to word embeddings. Simon Šuster University of Groningen
From perceptrons to word embeddings Simon Šuster University of Groningen Outline A basic computational unit Weighting some input to produce an output: classification Perceptron Classify tweets Written
More informationJiu Zhang Suan Shu and the Gauss Algorithm for Linear Equations
Documenta Math. 9 Jiu Zhang Suan Shu and the Gauss Algorithm for Linear Equations Ya-xiang Yuan 2010 Mathematics Subject Classification: 01A25, 65F05 Keywords and Phrases: Linear equations, elimination,
More informationSupporting Information. Graphene Textile Strain Sensor with Negative Resistance Variation for Human Motion
Supporting Information Graphene Textile Strain Sensor with Negative Resistance Variation for Human Motion Detection Zhen Yang, Yu Pang, Xiao-lin Han, Yifan Yang, Jiang Ling, Muqiang Jian, Yingying Zhang,
More informationOutline. Offline Evaluation of Online Metrics Counterfactual Estimation Advanced Estimators. Case Studies & Demo Summary
Outline Offline Evaluation of Online Metrics Counterfactual Estimation Advanced Estimators 1. Self-Normalized Estimator 2. Doubly Robust Estimator 3. Slates Estimator Case Studies & Demo Summary IPS: Issues
More informationCovariance Tracking Algorithm on Bilateral Filtering under Lie Group Structure Yinghong Xie 1,2,a Chengdong Wu 1,b
Applied Mechanics and Materials Online: 014-0-06 ISSN: 166-748, Vols. 519-50, pp 684-688 doi:10.408/www.scientific.net/amm.519-50.684 014 Trans Tech Publications, Switzerland Covariance Tracking Algorithm
More informationRandom Coattention Forest for Question Answering
Random Coattention Forest for Question Answering Jheng-Hao Chen Stanford University jhenghao@stanford.edu Ting-Po Lee Stanford University tingpo@stanford.edu Yi-Chun Chen Stanford University yichunc@stanford.edu
More informationNatural Language Processing and Recurrent Neural Networks
Natural Language Processing and Recurrent Neural Networks Pranay Tarafdar October 19 th, 2018 Outline Introduction to NLP Word2vec RNN GRU LSTM Demo What is NLP? Natural Language? : Huge amount of information
More informationGeneralization to a zero-data task: an empirical study
Generalization to a zero-data task: an empirical study Université de Montréal 20/03/2007 Introduction Introduction and motivation What is a zero-data task? task for which no training data are available
More informationVariational Decoding for Statistical Machine Translation
Variational Decoding for Statistical Machine Translation Zhifei Li, Jason Eisner, and Sanjeev Khudanpur Center for Language and Speech Processing Computer Science Department Johns Hopkins University 1
More informationStatistical Methods for NLP
Statistical Methods for NLP Language Models, Graphical Models Sameer Maskey Week 13, April 13, 2010 Some slides provided by Stanley Chen and from Bishop Book Resources 1 Announcements Final Project Due,
More informationThe effect of speaking rate and vowel context on the perception of consonants. in babble noise
The effect of speaking rate and vowel context on the perception of consonants in babble noise Anirudh Raju Department of Electrical Engineering, University of California, Los Angeles, California, USA anirudh90@ucla.edu
More informationSubstroke Approach to HMM-based On-line Kanji Handwriting Recognition
Sixth International Conference on Document nalysis and Recognition (ICDR 2001), pp.491-495 (2001-09) Substroke pproach to HMM-based On-line Kanji Handwriting Recognition Mitsuru NKI, Naoto KIR, Hiroshi
More informationHow to Write a Lab Report
How to Write a Lab Report Each section of your report should be clearly identified. Reports must be done on the computer. If you do not have access to a computer at home, you will have to use the computers
More informationMath-2 Section 1-1. Number Systems
Math- Section 1-1 Number Systems Natural Numbers Whole Numbers Lesson 1-1 Vocabulary Integers Rational Numbers Irrational Numbers Real Numbers Imaginary Numbers Complex Numbers Closure Why do we need numbers?
More informationLiquid-in-glass thermometer
Liquid-in-glass thermometer Objectives The objective of this experiment is to introduce some basic concepts in measurement, and to develop good measurement habits. In the first section, we will develop
More informationQuantum secret sharing based on quantum error-correcting codes
Quantum secret sharing based on quantum error-correcting codes Zhang Zu-Rong( ), Liu Wei-Tao( ), and Li Cheng-Zu( ) Department of Physics, School of Science, National University of Defense Technology,
More informationComputational Oracle Inequalities for Large Scale Model Selection Problems
for Large Scale Model Selection Problems University of California at Berkeley Queensland University of Technology ETH Zürich, September 2011 Joint work with Alekh Agarwal, John Duchi and Clément Levrard.
More informationStochastic Gradient Descent. CS 584: Big Data Analytics
Stochastic Gradient Descent CS 584: Big Data Analytics Gradient Descent Recap Simplest and extremely popular Main Idea: take a step proportional to the negative of the gradient Easy to implement Each iteration
More informationThe Noisy Channel Model and Markov Models
1/24 The Noisy Channel Model and Markov Models Mark Johnson September 3, 2014 2/24 The big ideas The story so far: machine learning classifiers learn a function that maps a data item X to a label Y handle
More informationLinear & nonlinear classifiers
Linear & nonlinear classifiers Machine Learning Hamid Beigy Sharif University of Technology Fall 1394 Hamid Beigy (Sharif University of Technology) Linear & nonlinear classifiers Fall 1394 1 / 34 Table
More informationMulti-theme Sentiment Analysis using Quantified Contextual
Multi-theme Sentiment Analysis using Quantified Contextual Valence Shifters Hongkun Yu, Jingbo Shang, MeichunHsu, Malú Castellanos, Jiawei Han Presented by Jingbo Shang University of Illinois at Urbana-Champaign
More informationAd Placement Strategies
Case Study 1: Estimating Click Probabilities Tackling an Unknown Number of Features with Sketching Machine Learning for Big Data CSE547/STAT548, University of Washington Emily Fox 2014 Emily Fox January
More informationHybrid Machine Learning Algorithms
Hybrid Machine Learning Algorithms Umar Syed Princeton University Includes joint work with: Rob Schapire (Princeton) Nina Mishra, Alex Slivkins (Microsoft) Common Approaches to Machine Learning!! Supervised
More informationSYMBOL RECOGNITION IN HANDWRITTEN MATHEMATI- CAL FORMULAS
SYMBOL RECOGNITION IN HANDWRITTEN MATHEMATI- CAL FORMULAS Hans-Jürgen Winkler ABSTRACT In this paper an efficient on-line recognition system for handwritten mathematical formulas is proposed. After formula
More informationNoise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic Approximation Algorithm
EngOpt 2008 - International Conference on Engineering Optimization Rio de Janeiro, Brazil, 0-05 June 2008. Noise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic
More informationDM-Group Meeting. Subhodip Biswas 10/16/2014
DM-Group Meeting Subhodip Biswas 10/16/2014 Papers to be discussed 1. Crowdsourcing Land Use Maps via Twitter Vanessa Frias-Martinez and Enrique Frias-Martinez in KDD 2014 2. Tracking Climate Change Opinions
More informationChapter 1 Introduction, Measurement, Estimating
Chapter 1 Introduction, Measurement, Estimating The Nature of Science Units of Chapter 1 Physics and Its Relation to Other Fields Models, Theories, and Laws Measurement and Uncertainty; Significant Figures
More informationLearning Features from Co-occurrences: A Theoretical Analysis
Learning Features from Co-occurrences: A Theoretical Analysis Yanpeng Li IBM T. J. Watson Research Center Yorktown Heights, New York 10598 liyanpeng.lyp@gmail.com Abstract Representing a word by its co-occurrences
More informationEmpirical Methods in Natural Language Processing Lecture 10a More smoothing and the Noisy Channel Model
Empirical Methods in Natural Language Processing Lecture 10a More smoothing and the Noisy Channel Model (most slides from Sharon Goldwater; some adapted from Philipp Koehn) 5 October 2016 Nathan Schneider
More informationBoolean and Vector Space Retrieval Models
Boolean and Vector Space Retrieval Models Many slides in this section are adapted from Prof. Joydeep Ghosh (UT ECE) who in turn adapted them from Prof. Dik Lee (Univ. of Science and Tech, Hong Kong) 1
More informationCHBE320 LECTURE XI CONTROLLER DESIGN AND PID CONTOLLER TUNING. Professor Dae Ryook Yang
CHBE320 LECTURE XI CONTROLLER DESIGN AND PID CONTOLLER TUNING Professor Dae Ryook Yang Spring 2018 Dept. of Chemical and Biological Engineering 11-1 Road Map of the Lecture XI Controller Design and PID
More informationAnalog Computing: a different way to think about building a (quantum) computer
Analog Computing: a different way to think about building a (quantum) computer November 24, 2016 1 What is an analog computer? Most of the computers we have around us today, such as desktops, laptops,
More informationBoolean and Vector Space Retrieval Models CS 290N Some of slides from R. Mooney (UTexas), J. Ghosh (UT ECE), D. Lee (USTHK).
Boolean and Vector Space Retrieval Models 2013 CS 290N Some of slides from R. Mooney (UTexas), J. Ghosh (UT ECE), D. Lee (USTHK). 1 Table of Content Boolean model Statistical vector space model Retrieval
More informationChemical Research in Chinese Universities
Chemical Research in Chinese Universities Vol.24 No.5 September 2008 CONTENTS Articles Comparison of the Sol-gel Method with the Coprecipitation Technique for Preparation of Hexagonal Barium Ferrite WANG
More informationNatural Language Processing SoSe Words and Language Model
Natural Language Processing SoSe 2016 Words and Language Model Dr. Mariana Neves May 2nd, 2016 Outline 2 Words Language Model Outline 3 Words Language Model Tokenization Separation of words in a sentence
More informationAd Placement Strategies
Case Study : Estimating Click Probabilities Intro Logistic Regression Gradient Descent + SGD AdaGrad Machine Learning for Big Data CSE547/STAT548, University of Washington Emily Fox January 7 th, 04 Ad
More informationMathematical notation and writing
Mathematical notation and writing 19 March 2013 Mathematical notation and writing Mathematical Writing Writing is difficult. Writing Mathematics is very difficult. Keep your prose simple and direct. Use
More informationCALCULATION METHOD OF DYNAMIC CHARACTERISTICS OF FLOATING RAFT ISOLATION SYSTEM
CALCULATION METHOD OF DYNAMIC CHARACTERISTICS OF FLOATING RAFT ISOLATION SYSTEM Wang Qing, He Xuesong, Du Kun and Li Zhaohui China Ship Development and design center, National Key Laboratory on ship vibration
More informationThe Book: Where we are and where we re going. CSE 190: Reinforcement Learning: An Introduction. Chapter 7: Eligibility Traces. Simple Monte Carlo
CSE 190: Reinforcement Learning: An Introduction Chapter 7: Eligibility races Acknowledgment: A good number of these slides are cribbed from Rich Sutton he Book: Where we are and where we re going Part
More information