Kai-Wei Chang UCLA. What It Takes to Control Societal Bias in Natural Language Processing. References:
|
|
- Vincent Roberts
- 5 years ago
- Views:
Transcription
1 What It Takes to Control Societal Bias in Natural Language Processing Kai-Wei Chang UCLA References: Kai-Wei Chang (kwchang.net/talks/sp.html) 1
2 A father and son get in a car crash and are rushed to the hospital. The father dies. The boy is taken to the operating room and the surgeon says, I can t operate on this boy, because he s my son. Can you explain why? Kai-Wei Chang (kwchang.net/talks/sp.html) 2
3 Implicit association test (IAT) Kai-Wei Chang (kwchang.net/talks/sp.html) 3
4 Concepts in semantic memory are assumed to be linked together with associated concepts having stronger links than unrelated concepts (Collins and Loftus, 1975). - Kai-Wei Chang (kwchang.net/talks/sp.html) 4
5 Concepts in semantic memory are assumed to be linked together with associated concepts having stronger links than unrelated concepts (Collins and Loftus, 1975). Kai-Wei Chang (kwchang.net/talks/sp.html) 5
6 So does computer Data with Societal Bias Model with Societal Bias Kai-Wei Chang (kwchang.net/talks/sp.html) 6
7 Word Embeddings can be Dreadfully Sexist [nips16] w/ Tolga Bolukbasi, James Zou, Venkatesh Saligrama, Adam Kalai v v "#$ v &'"#$ + v )$*+, v #)$/ he: brother beer physician programmer professor she: sister cocktail registered_nurse homemaker associate professor We use Google w2v embedding trained from the news Kai-Wei Chang (kwchang.net/talks/sp.html) 7
8
9 Related works Aylin, Joanna, and Arvind (2017) measure the biases in embedding using Implicit Association Test (IAT) and demonstrate it contain human-like biases Garg, Schiebinger, Jurafsky, Zou (2017) Word embeddings quantify 100 years of gender and ethnic stereotypes: 9
10 Gender Bias in Coref [NAACL 2018] Concurrent work (Rudinger et al., also studied gender bias in Coref. 10
11 Africa-American English Non Africa-American English Kai-Wei Chang (kwchang.net/talks/sp.html) 11
12 errors Majority Majority Minority Minority error rate: 6/30 = 80% error rate: 6/30 = 80% Kai-Wei Chang (kwchang.net/talks/sp.html) 12
13 Human Bias in Structured Prediction Models [EMNLP 17*] w/ Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez What s the agent for this image? Cooking Role Object agent food container tool place woman? vegetable bowl knife kitchen An example from a vsrl (visual Semantic Role Labeling) system *Best Long Paper Award at EMNLP 17 Kai-Wei Chang (kwchang.net/talks/sp.html) 13/9
14
15
16 Algorithmic Bias in Applications cooking dusting faucet fork World Dataset Model Credit: Mark Yatskar 16 16
17 Algorithmic Bias in Applications woman cooking cooking dusting faucet fork World Dataset Model Credit: Mark Yatskar 17 17
18 Algorithmic Bias in Applications woman cooking man fixing faucet cooking dusting faucet fork World Dataset Model Credit: Mark Yatskar 18 18
19 When AI products exhibit Societal Bias Kai-Wei Chang (kwchang.net/talks/sp.html) 19
20 Kai-Wei Chang (kwchang.net/talks/sp.html) 20
21 What It Takes to Control Societal Bias in NLP? Gender discrimination is illegal in the United States. Stanford Parser Kai-Wei Chang (kwchang.net/talks/sp.html) 21
22 A carton of ML (NLP) pipeline Prediction (Structured) Inference Representation E.g., word embedding, Knowledge bases. Etc. Auxiliary Corpus Data Kai-Wei Chang (kwchang.net/talks/sp.html) 22
23 Outline v Controlling Gender Bias in Representation Level A study of removing bias in Word Embedding v Reducing Gender Bias in Data Level A case study on co-reference resolution v Reducing Gender Bias in Inference Level Guiding predictions by corpus-wise constraints Kai-Wei Chang (kwchang.net/talks/sp.html) 23
24 Word Embeddings can be Dreadfully Sexist [nips16] w/ Tolga Bolukbasi, James Zou, Venkatesh Saligrama, Adam Kalai v v "#$ v &'"#$ + v )$*+, v #)$/ he: brother barbershop beer physician programmer professor she: sister salon cocktail registered_nurse homemaker associate professor We use Google w2v embedding trained from the news Kai-Wei Chang (kwchang.net/talks/sp.html) 24
25 Geometry of Gender and Bias v Identifying the gender subspace Top 10 Eigenvalue Top 10 Eigenvalue PCA ( he - she, father - mother, ) Gender Pair PCA ( dog - cat, house - building, ) Random Pair Kai-Wei Chang (kwchang.net/talks/sp.html) 25
26 Reducing bias SEXIST FEMALE MALE DEFINITIONAL
27 SEXIST FEMALE tote browsing tanning scrimmage dress sewing brilliant nurse cocky genius homemaker MALE DEFINITIONAL (related [Schmidt 15])
28 Approach 1: Project out gender dimension (hard version) v Step 1: Remove gender dimension from gender-neutral words
29 Approach 1: Post-processing (Hard) Project Out Gender Dimension v Step 2: re-center gender-definitional pairs
30 Approach 2: Post-processing (Soft) Find a linear transformation T of the gender-neutral words to reduce the gender component while not moving the words too much. W = matrix of all word vectors. N = matrix of neutral word vectors. min T (TW) T (TW) W T W 2 F + (TN) T (TB) 2 F don t move too much minimize gender component
31 Approach 3: Learning Gender-Neutral Word Embedding [Jieyu+EMNLP18] v How can we not to encode gender information in word vectors? corpus man, woman father, mother he, she Kai-Wei Chang (kwchang.net/talks/sp.html) 31
32 Approach 3: Learning Gender-Neutral Word Embeddings [Jieyu+ EMNLP18] dimensions for other latent aspects w 1 1-1? mother father doctor dimensions reserve for gender information Kai-Wei Chang (kwchang.net/talks/sp.html) 32
33 w 2 w 1 Kai-Wei Chang (kwchang.net/talks/sp.html) 33
34 Are these debiased vectors actually useful? Kai-Wei Chang (kwchang.net/talks/sp.html) 34
35 Outline v Controlling Gender Bias in Representation Level A study of removing bias in Word Embedding v Reducing Gender Bias in Data Level A case study on co-reference resolution v Reducing Gender Bias in Inference Level Guiding predictions by corpus-wise constraints Kai-Wei Chang (kwchang.net/talks/sp.html) 35
36 Gender Bias in Coref [NAACL 2018] Concurrent work (Rudinger et al., also studied gender bias in Coref. 36
37 Wino-bias data v Stereotypical dataset v Anti-stereotypical dataset Kai-Wei Chang (kwchang.net/talks/sp.html) 37
38 Gender bias in Coref System E2E E2E (Debiased WE) E2E (Full model) Steoetype Anti-Steoretype Avg Kai-Wei Chang (kwchang.net/talks/sp.html) 38
39 Source of gender bias Co-reference Prediction Use gender-neutral embedding (Structured) Inference Representation Word Embedding Data 80% entities in OntoNotes are male Kai-Wei Chang (kwchang.net/talks/sp.html) 39
40 Gender bias in Coref System E2E E2E (Debiased WE) E2E (Full model) Steoetype Anti-Steoretype Avg Kai-Wei Chang (kwchang.net/talks/sp.html) 40
41 How to deal with bias in data v Idea: simulate sentence in opposite gender John went to his house F2 went to her house Named Entity are anonymized Gender words are swapped Kai-Wei Chang (kwchang.net/talks/sp.html) 41
42 Gender bias in Coref System E2E E2E (Debiased WE) E2E (Full model) Steoetype Anti-Steoretype Avg Kai-Wei Chang (kwchang.net/talks/sp.html) 42
43 Outline v Controlling Gender Bias in Representation Level A study of removing bias in Word Embedding v Reducing Gender Bias in Data Level A case study on co-reference resolution v Reducing Gender Bias in Inference Level Guiding predictions by corpus-wise constraints Kai-Wei Chang (kwchang.net/talks/sp.html) 43
44 Human Bias in Structured Prediction Models [EMNLP 17*] w/ Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez What s the agent for this image? Cooking Role Object agent food container tool place woman? vegetable bowl knife kitchen An example from a vsrl (visual Semantic Role Labeling) system *Best Long Paper Award at EMNLP 17 Kai-Wei Chang (kwchang.net/talks/sp.html) 44/9
45 imsitu Visual Semantic Role Labeling (vsrl) Convolutional Neural Network COOKING ROLES AGENT FOOD CONTAINER TOOL (events) NOUNS woman vegetable pot spatula Kai-Wei Chang (kwchang.net/talks/sp.html) Yatskar et al. CVPR 16, Yang et al. NAACL 16, Gupta and Malik arxiv 16 Regression Conditional Random Field 45
46 COCO Multi-Label Classification (MLC) Convolutional Neural Network WOMAN PIZZA yes ZEBRA no FRIDGE yes CAR no Regression Conditional Random Field Kai-Wei Chang (kwchang.net/talks/sp.html) 46
47 Defining Dataset Bias (events) 47
48 Defining Dataset Bias (objects) Training Gender Ratio ( noun) 48
49 Gender Dataset Bias Kai-Wei Chang (kwchang.net/talks/sp.html) 49
50 Model Bias Amplification Kai-Wei Chang (kwchang.net/talks/sp.html) 50
51 Model Bias Amplification Kai-Wei Chang (kwchang.net/talks/sp.html) 51
52 Reducing Bias Amplification (RBA) Dataset Model RBA v Corpus level constraints on model output (ILP) v Doesn t require model retraining v Reuse model inference through Lagrangian relaxation v Can be applied to any structured model Kai-Wei Chang (kwchang.net/talks/sp.html) 52
53 Reducing Bias Amplification (RBA) 53
54 Reducing Bias Amplification (RBA) Sontag et al., 2011; Rush and Collins, 2012; Chang and Collins, 2011; Peng et al., 2015, Chang et al., 2013; Dalvi,
55 Reducing Bias Amplification (RBA) Lagrangian : λ 4 0 Sontag et al., 2011; Rush and Collins, 2012; Chang and Collins, 2011; Peng et al., 2015, Chang et al., 2013; Dalvi,
56 Lagrangian Relaxation Sontag et al., 2011; Rush and Collins, 2012; Chang and Collins, 2011; Peng et al., 2015, Chang et al., 2013; Dalvi,
57 Lagrangian Relaxation Sontag et al., 2011; Rush and Collins, 2012; Chang and Collins, 2011; Peng et al., 2015, Chang et al., 2013; Dalvi,
58 Lagrangian Relaxation Sontag et al., 2011; Rush and Collins, 2012; Chang and Collins, 2011; Peng et al., 2015, Chang et al., 2013; Dalvi,
59 Lagrangian Relaxation 59 Sontag et al., 2011; Rush and Collins, 2012; Chang and Collins, 2011; Peng et al., 2015, Chang et al., 2013; Dalvi, 2015
60 Gender Bias De-amplification in imsitu Male bias 60
61 Gender Bias De-amplification in imsitu Male bias 61
62 UCLA NLP NLP Applications Efficient Algorithms activity agent food cooking woman vegetable Learning from weak signals Fairness (data biases) 62
63 Conclusions v Like other AI systems, NLP systems affect by societal bias present in data v The issues cause unfair predictions are not new vdomain adaptation / Data collection bias v Ultimate goal: robust NLP systems for social good v References: Kai-Wei Chang (kwchang.net/talks/sp.html) 63
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. Md Musa Leibniz University of Hannover
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings Md Musa Leibniz University of Hannover Agenda Introduction Background Word2Vec algorithm Bias in the data generated from
More informationarxiv: v1 [cs.cl] 18 Apr 2018
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods Jieyu Zhao Tianlu Wang Mark Yatskar Vicente Ordonez Kai-Wei Chang University of California, Los Angeles {jyzhao, kwchang}@cs.ucla.edu
More informationGender Bias in Coreference Resolution: Evaluation and Debiasing Methods
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods Jieyu Zhao Tianlu Wang Mark Yatskar Vicente Ordonez Kai-Wei Chang University of California, Los Angeles {jyzhao, kwchang}@cs.ucla.edu
More informationCS221 / Autumn 2017 / Liang & Ermon. Lecture 19: Conclusion
CS221 / Autumn 2017 / Liang & Ermon Lecture 19: Conclusion Outlook AI is everywhere: IT, transportation, manifacturing, etc. AI being used to make decisions for: education, credit, employment, advertising,
More informationA Gendered Perspective on Artificial Intelligence
A Gendered Perspective on Artificial Intelligence Smriti Parsheera National Institute of Public Finance & Policy smriti.parsheera@gmail.com Overview The origins of AI and its gender dimensions The questions:
More informationApplied Machine Learning, Lecture 11: Ethical and legal considerations; domain effects and domain adaptation
Applied Machine Learning, Lecture 11: Ethical and legal considerations; domain effects and domain adaptation Richard Johansson including some slides borrowed from Barbara Plank overview introduction bias
More informationBuilding Evaluation Scales for NLP using Item Response Theory
Building Evaluation Scales for NLP using Item Response Theory John Lalor CICS, UMass Amherst Joint work with Hao Wu (BC) and Hong Yu (UMMS) Motivation Evaluation metrics for NLP have been mostly unchanged
More informationSummary on A few Testing Machine learning papers
Summary on A few Testing Machine learning papers Presented by : Ji Gao 1 Department of Computer Science, University of Virginia https://qdata.github.io/deep2read/ August 26, 2018 August 26, 2018 1 / 86
More informationLatent Space Based Text Generation Using Attention Models
Latent Space Based Text Generation Using Attention Models Jules Gagnon-Marchand Prepared for NLP Workshop for MILA Aug. 31, 2018 Introduction: Motivation Text Generation is important: Any AI based task
More informationFoundations of Natural Language Processing Lecture 13 Heads, Dependency parsing
Foundations of Natural Language Processing Lecture 13 Heads, Dependency parsing Alex Lascarides (slides from Alex Lascarides, Henry Thompson, Nathan Schneider and Sharon Goldwater) 6 March 2018 Alex Lascarides
More informationToday we will... Foundations of Natural Language Processing Lecture 13 Heads, Dependency parsing. Evaluating parse accuracy. Evaluating parse accuracy
Today we will... Foundations of Natural Language Processing Lecture 13 Heads, Dependency parsing Alex Lascarides (slides from Alex Lascarides, Henry Thompson, Nathan chneider and haron Goldwater) 6 March
More informationarxiv: v1 [cs.cl] 22 Nov 2017
Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes arxiv:1711.08412v1 [cs.cl] 22 Nov 2017 Nikhil Garg Stanford University nkgarg@stanford.edu Londa Schiebinger Stanford University schieb@stanford.edu
More informationStereotyping and Bias in the Flickr30k Dataset
Stereotyping and Bias in the Flickr30k Dataset Emiel van Miltenburg Vrije Universiteit Amsterdam Multimodal Corpora: Computer vision and language processing (MMC 2016) Background Automatic image description
More informationIMPLICIT BIAS: UNDERSTANDING AND ADDRESSING ITS IMPACT. ALGA Regional Training Dr. Markisha Smith October 4, 2018
IMPLICIT BIAS: UNDERSTANDING AND ADDRESSING ITS IMPACT ALGA Regional Training Dr. Markisha Smith October 4, 2018 Develop and/or expand on an understanding of implicit bias. GOALS FOR TODAY S SESSION Consider
More informationThe University of Tokyo, NVAIL Partner Yoshitaka Ushiku
Recognize, Describe, and Generate: Introduction of Recent Work at MIL The University of Tokyo, NVAIL Partner Yoshitaka Ushiku MIL: Machine Intelligence Laboratory Beyond Human Intelligence Based on Cyber-Physical
More informationMS&E 226: Small Data
MS&E 226: Small Data Lecture 10: Introduction to inference (v2) Ramesh Johari ramesh.johari@stanford.edu 1 / 17 What is inference? 2 / 17 Where did our data come from? Recall our sample is: Y, the vector
More informationConcepts and Categories
Concepts and Categories Functions of Concepts By dividing the world into classes of things to decrease the amount of information we need to learn, perceive, remember, and recognise: cognitive economy They
More informationarxiv: v1 [cs.cl] 25 Jul 2018
Judging a Book by its Description : Analyzing Gender Stereotypes in the Man Bookers Prize Winning Fiction Nishtha Madaan 1, Sameep Mehta 1, Shravika Mittal 2, Ashima Suvarna 3 1 IBM Research AI-India 2
More informationTranslating Videos to Natural Language Using Deep Recurrent Neural Networks
Translating Videos to Natural Language Using Deep Recurrent Neural Networks Subhashini Venugopalan UT Austin Huijuan Xu UMass. Lowell Jeff Donahue UC Berkeley Marcus Rohrbach UC Berkeley Subhashini Venugopalan
More informationInsights into Analogy Completion from the Biomedical Domain
Insights into Analogy Completion from the Biomedical Domain Denis Newman-Griffis, Albert Lai, Eric Fosler-Lussier The Ohio State University National Institutes of Health, Clinical Center Washington University
More informationGeneralizing Dependency Features for Opinion Mining
Generalizing Dependency Features for Mahesh Joshi 1 and Carolyn Rosé 1,2 1 Language Technologies Institute 2 Human-Computer Interaction Institute Carnegie Mellon University ACL-IJCNLP 2009 Short Papers
More informationActive Deformable Part Models Inference
Active Deformable Part Models Inference Menglong Zhu Nikolay Atanasov George J. Pappas Kostas Daniilidis GRASP Laboratory, University of Pennsylvania 3330 Walnut Street, Philadelphia, PA 19104, USA Abstract.
More informationConvolutional Neural Networks for Text Classification
Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is
More informationEVIDENCE AND INVESTIGATION: Booklet 1
EVIDENCE AND INVESTIGATION: Booklet 1 NAME: Key Questions: What is a detective? Detective: What is Forensic Science or Forensic Investigation: How can we use information and evidence to fight crime? Evidence:
More informationAction Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem
Action Recognition Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem This section: advanced topics Convolutional neural networks in vision Action recognition Vision and Language 3D
More informationPast Progressive Story 1 (Past Continuous)
Past Progressive Story 1, Page 1 Past Progressive Story 1 (Past Continuous) By Really Learn English Visit the Past Progressive (Continuous) Section for More Resources Who was she? Where was she? What was
More informationMotivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.
Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing
More informationSequential Predictions Recurrent Neural Networks
CS 2770: Computer Vision Sequential Predictions Recurrent Neural Networks Prof. Adriana Kovashka University of Pittsburgh March 28, 2017 One Motivation: Descriptive Text for Images It was an arresting
More informationImplicit Association Test (IAT)
Implicit Association Test (IAT) Project Implicit take the test https://implicit.harvard.edu/implicit/ Project Implicit Social Attitudes Continue as Guest Select: Gender-Career IAT Answer quickly 1 January
More informationLearning the Fine-Grained Information Status of Discourse Entities
Learning the Fine-Grained Information Status of Discourse Entities Altaf Rahman and Vincent Ng Human Language Technology Research Institute The University of Texas at Dallas Plan for the talk What is Information
More informationInterpreting Deep Neural Networks and their Predictions
Fraunhofer Image Processing Heinrich Hertz Institute Interpreting Deep Neural Networks and their Predictions Wojciech Samek ML Group, Fraunhofer HHI (joint work with S. Lapuschkin, A. Binder, G. Montavon,
More informationRecurrent Neural Networks
CS 2750: Machine Learning Recurrent Neural Networks Prof. Adriana Kovashka University of Pittsburgh March 14, 2017 One Motivation: Descriptive Text for Images It was an arresting face, pointed of chin,
More informationPreviously Triggered Dependency Search Overrides Local Coherence Effects
Previously Triggered Dependency Search Overrides Local Coherence Effects 20 TH AMLAP 2014 04 SEPTEMBER LAUREN ACKERMAN NINA KAZANINA MASAYA YOSHIDA The Question Does online long-distance dependency formation
More informationInferring Clinical Correlations from EEG Reports with Deep Neural Learning
Inferring Clinical Correlations from EEG Reports with Deep Neural Learning Methods for Identification, Classification, and Association using EHR Data S23 Travis R. Goodwin (Presenter) & Sanda M. Harabagiu
More informationBayesian Face Recognition Using Gabor Features
Bayesian Face Recognition Using Gabor Features Xiaogang Wang, Xiaoou Tang Department of Information Engineering The Chinese University of Hong Kong Shatin, Hong Kong {xgwang1,xtang}@ie.cuhk.edu.hk Abstract
More information. Semi-automatic WordNet Linking using Word Embeddings. Kevin Patel, Diptesh Kanojia and Pushpak Bhattacharyya Presented by: Ritesh Panjwani
Semi-automatic WordNet Linking using Word Embeddings Kevin Patel, Diptesh Kanojia and Pushpak Bhattacharyya Presented by: Ritesh Panjwani January 11, 2018 Kevin Patel WordNet Linking via Embeddings 1/22
More informationHierarchical Convolutional Features for Visual Tracking
Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate
More informationIdentification of Neuroimaging Biomarkers
Identification of Neuroimaging Biomarkers Dan Goodwin, Tom Bleymaier, Shipra Bhal Advisor: Dr. Amit Etkin M.D./PhD, Stanford Psychiatry Department Abstract We present a supervised learning approach to
More informationComputational Ethics for NLP
Computational Ethics for NLP Summary Yulia Tsvetkov ytsvetko@cs.cmu.edu What s the Difference? AI and People Ethics and NLP The common misconception is that language has to do with words and what they
More informationMeasuring impact of a gender sensitisation program among children: Lessons from data collection in Haryana, India
Measuring impact of a gender sensitisation program among children: Lessons from data collection in Haryana, India Tarun Jain Indian School of Business, Hyderabad, India September 2, 2014 Tarun Jain (ISB)
More informationImplicit Bias. Primer & Refresher The Kirwan Institute. Kelly Capatosto, Senior Research Associate & Jillian Olinger, Senior Research Associate
Implicit Bias Primer & Refresher The Kirwan Institute Kelly Capatosto, Senior Research Associate & Jillian Olinger, Senior Research Associate ABOUT KIRWAN We work to create a just & inclusive society where
More informationMinimum Risk Training For Neural Machine Translation. Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu
Minimum Risk Training For Neural Machine Translation Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu ACL 2016, Berlin, German, August 2016 Machine Translation MT: using computer
More informationFactoid Question Answering
Factoid Question Answering CS 898 Project June 12, 2017 Salman Mohammed David R. Cheriton School of Computer Science University of Waterloo Motivation Source: https://www.apple.com/newsroom/2017/01/hey-siri-whos-going-to-win-the-super-bowl/
More informationImage Captioning using Reinforcement Learning. Presentation by: Samarth Gupta
Image Captioning using Reinforcement Learning Presentation by: Samarth Gupta 1 Introduction Summary Supervised Models Image captioning as RL problem Actor Critic Architecture Policy Gradient architecture
More informationShu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge 4. Fine-grained classification with holistic representation
More informationKeyword-driven Image Captioning via Context-dependent Bilateral LSTM
Keyword-driven Image Captioning via Context-dependent Bilateral LSTM Xiaodan Zhang 1,2, Shuqiang Jiang 2, Qixiang Ye 2, Jianbin Jiao 2, Rynson W.H. Lau 1 1 City University of Hong Kong 2 University of
More informationA Look at National Awards Robin Autenrieth Co-PI, ADVANCE Program Interim Department Head, Civil Engineering
A Look at National Awards Robin Autenrieth Co-PI, ADVANCE Program Interim Department Head, Civil Engineering This material is based upon work supported by the National Science Foundation under NSF Cooperative
More informationDetecting Patient Complexity from Free Text Notes Using a Hybrid AI Approach
Detecting Patient Complexity from Free Text Notes Using a Hybrid AI Approach Malcolm Pradhan, CMO MBBS, PhD, FACHI Daniel Padilla, ML Engineer BEng,, PhD Alcidion Corporation Overview Alcidion s Natural
More informationCorpus Construction and Semantic Analysis of Indonesian Image Description
Corpus Construction and Semantic Analysis of Indonesian Image Description Khumaisa Nur aini 1,3, Johanes Effendi 1, Sakriani Sakti 1,2, Mirna Adriani 3, Sathosi Nakamura 1,2 1 Nara Institute of Science
More informationImplicit Bias for Homeownership Professionals Susan Naimark
Implicit Bias for Homeownership Professionals Susan Naimark www.naimark.org 1 2 Introductions 1. Name 2. Your role 3. What you most hope to get out of this workshop (in one sentence please!) Agenda ì 1.
More informationLearning to Disambiguate by Asking Discriminative Questions Supplementary Material
Learning to Disambiguate by Asking Discriminative Questions Supplementary Material Yining Li 1 Chen Huang 2 Xiaoou Tang 1 Chen Change Loy 1 1 Department of Information Engineering, The Chinese University
More informationarxiv: v1 [stat.ml] 23 Jan 2017
Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London
More informationCOMP9444 Neural Networks and Deep Learning 5. Convolutional Networks
COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations
More informationStatistical considerations in indirect comparisons and network meta-analysis
Statistical considerations in indirect comparisons and network meta-analysis Said Business School, Oxford, UK March 18-19, 2013 Cochrane Comparing Multiple Interventions Methods Group Oxford Training event,
More informationMemory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports
Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports Ramon Maldonado, BS, Travis Goodwin, PhD Sanda M. Harabagiu, PhD The University
More informationMeasuring and Mitigating Unintended Bias in Text Classification
Measuring and Mitigating Unintended Bias in Text Classification Lucas Dixon ldixon@google.com John Li jetpack@google.com Jeffrey Sorensen sorenj@google.com Nithum Thain nthain@google.com Lucy Vasserman
More informationWhat Effect Do Schemas Have On The Recall Of
What Effect Do Schemas Have On The Recall Of Memories AIM:Bartlett aimed to investigate the effect of culture on memory. memory ability/ability to recall and have advantageous effects if asked to do a
More informationDeep Learning based Information Extraction Framework on Chinese Electronic Health Records
Deep Learning based Information Extraction Framework on Chinese Electronic Health Records Bing Tian Yong Zhang Kaixin Liu Chunxiao Xing RIIT, Beijing National Research Center for Information Science and
More informationBayes Linear Statistics. Theory and Methods
Bayes Linear Statistics Theory and Methods Michael Goldstein and David Wooff Durham University, UK BICENTENNI AL BICENTENNIAL Contents r Preface xvii 1 The Bayes linear approach 1 1.1 Combining beliefs
More informationChapter 5: Producing Data
Chapter 5: Producing Data Key Vocabulary: observational study vs. experiment confounded variables population vs. sample sampling vs. census sample design voluntary response sampling convenience sampling
More informationModes of Measurement. Outline. Modes of Measurement. PSY 395 Oswald
Modes of Measurement PSY 395 Oswald Outline Modes of Measurement Direct questioning Paper-and-pencil Face-to-face Telephone Interviews Newer Modes Internet Experience Sampling Implicit measures Third-party
More informationThe AB of Random Effects Models
The AB of Random Effects Models Rick Chappell, Ph.D. Professor, Department of Biostatistics and Medical Informatics University of Wisconsin Madison ADC Meetings, Baltimore, 10/2016 Outline A. Linear Models
More informationNatural Language Processing - A Survey MSR UW Summer Institute
Natural Language Processing - A Survey Talk @ MSR UW Summer Institute 2016 - Margaret Mitchell Cognition Group Microsoft Research Yejin Choi Computer Science & Engineering Accessibility in the Past Reading
More informationInterpretable & Transparent Deep Learning
Fraunhofer Image Processing Heinrich Hertz Institute Interpretable & Transparent Deep Learning Fraunhofer HHI, Machine Learning Group Wojciech Samek Northern Lights Deep Learning Workshop (NLDL 19) Tromsø,
More informationQuestion Answering: Research Challenges and Opportunities. Scott Wen-tau Yih Microsoft Research
Question Answering: Research Challenges and Opportunities Scott Wen-tau Yih Microsoft Research http://csunplugged.org/turing-test Recursive NN [Socher+ ICML-11] Deep Structured Semantic Model [Huang+
More informationAuthor's response to reviews
Author's response to reviews Title: Gender, ethnicity, health behaviour & self-rated health in Singapore Authors: Wei-Yen Lim (Lim_Wei_Yen@moh.gov.sg) Stefan Ma (Stefan_Ma@moh.gov.sg) Derrick Heng (Derrick_Heng@moh.gov.sg)
More informationIncorporating Word Correlation Knowledge into Topic Modeling. Pengtao Xie. Joint work with Diyi Yang and Eric Xing
Incorporating Word Correlation Knowledge into Topic Modeling Pengtao Xie Joint work with Diyi Yang and Eric Xing 1 Outline Motivation Incorporating Word Correlation Knowledge into Topic Modeling Experiments
More informationDomain Generalization and Adaptation using Low Rank Exemplar Classifiers
Domain Generalization and Adaptation using Low Rank Exemplar Classifiers 报告人 : 李文 苏黎世联邦理工学院计算机视觉实验室 李文 苏黎世联邦理工学院 9/20/2017 1 Outline Problems Domain Adaptation and Domain Generalization Low Rank Exemplar
More informationCS-E Deep Learning Session 4: Convolutional Networks
CS-E4050 - Deep Learning Session 4: Convolutional Networks Jyri Kivinen Aalto University 23 September 2015 Credits: Thanks to Tapani Raiko for slides material. CS-E4050 - Deep Learning Session 4: Convolutional
More informationDEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS
SEOUL Oct.7, 2016 DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS Gunhee Kim Computer Science and Engineering Seoul National University October
More information"Inferring Sibling Relatedness from the NLSY Youth and Children Data: Past, Present, and Future Prospects" Joseph Lee Rodgers, University of Oklahoma
"Inferring Sibling Relatedness from the NLSY Youth and Children Data: Past, Present, and Future Prospects" Joseph Lee Rodgers, University of Oklahoma Amber Johnson, Oregon Social Learning Center David
More informationVisual semantics: image elements. Symbols Objects People Poses
Visible Partisanship Polmeth XXXIII, Rice University, July 22, 2016 Convolutional Neural Networks for the Analysis of Political Images L. Jason Anastasopoulos ljanastas@uga.edu (University of Georgia,
More informationRevised Top Ten List of Things Wrong with the IAT
Revised Top Ten List of Things Wrong with the IAT Anthony G. Greenwald, University of Washington Attitudes Preconference SPSP - Austin, Texas January 29, 2004 Outline *6. Top 10 Unsolved problems in IAT
More informationJoint Inference for Heterogeneous Dependency Parsing
Joint Inference for Heterogeneous Dependency Parsing Guangyou Zhou and Jun Zhao National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences 95 Zhongguancun East Road,
More informationUnit 5 How to be healthy?
Sugestões de atividades Unit 5 How to be healthy? 7 INGLÊS Read the text below about a healthy diet called Raw Foodism and answer the questions. Raw Foodism Raw foodism is a diet based on uncooked and
More informationSmaller, faster, deeper: University of Edinburgh MT submittion to WMT 2017
Smaller, faster, deeper: University of Edinburgh MT submittion to WMT 2017 Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip
More informationarxiv: v2 [cs.cv] 27 Nov 2018
Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions arxiv:1811.08592v2 [cs.cv] 27 Nov 2018 Albert Haque 1 Michelle Guo 1 Adam S Miner 2,3 Li Fei-Fei 1 1 Department of Computer
More informationAttention. Concentrating and focusing of mental effort that is:
What is attention? Concentrating and focusing of mental effort that is: Page 1 o Selective--focus on some things while excluding others o Divisible--able to focus on more than one thing at the same time
More informationOrganizational. Architectures of Cognition Lecture 1. What cognitive phenomena will we examine? Goals of this course. Practical Assignments.
Architectures of Cognition Lecture 1 Niels Taatgen Artificial Intelligence Webpage: http://www.ai.rug.nl/avi 2 Organizational Practical assignments start Next Week Work in pairs 3 assignments Grade = (1/4)*assignments
More informationShu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with
More informationReliability of Ordination Analyses
Reliability of Ordination Analyses Objectives: Discuss Reliability Define Consistency and Accuracy Discuss Validation Methods Opening Thoughts Inference Space: What is it? Inference space can be defined
More informationAdversarial Removal of Demographic Attributes from Text Data
Adversarial Removal of Demographic Attributes from Text Data Yanai Elazar and Yoav Goldberg Computer Science Department, Bar-Ilan University, Israel Allen Institute for Artificial Intelligence {yanaiela,yoav.goldberg}@gmail.com
More informationSentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions?
Sentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions? Isa Maks and Piek Vossen Vu University, Faculty of Arts De Boelelaan 1105, 1081 HV Amsterdam e.maks@vu.nl, p.vossen@vu.nl
More informationIntroduction to MVPA. Alexandra Woolgar 16/03/10
Introduction to MVPA Alexandra Woolgar 16/03/10 MVP...what? Multi-Voxel Pattern Analysis (MultiVariate Pattern Analysis) * Overview Why bother? Different approaches Basics of designing experiments and
More informationShared Response Model Tutorial! What works? How can it help you? Po-Hsuan (Cameron) Chen and Hejia Hasson Lab! Feb 15, 2017!
Shared Response Model Tutorial! What works? How can it help you? Po-Hsuan (Cameron) Chen and Hejia Zhang!!! @ Hasson Lab! Feb 15, 2017! Outline! SRM Theory! SRM on fmri! Hands-on SRM with BrainIak! SRM
More informationOVERVIEW TUTORIAL BEHAVIORAL METHODS CLAIM: EMLAR VII EYE TRACKING: READING. Lecture (50 min) Short break (10 min) Computer Assignments (30 min)
EMLAR VII EYE TRACKING: READING Arnout Koornneef a.w.koornneef@uu.nl OVERVIEW TUTORIAL Lecture (50 min) Basic facts about reading Examples Advantages and disadvantages of eye tracking Short break (10 min)
More informationA Language Modeling Approach for Temporal Information Needs
A Language Modeling Approach for Temporal Information Needs Klaus Berberich, Srikanta Bedathur Omar Alonso, Gerhard Weikum 2010, March 29th ECIR 2010 Milton Keynes Motivation Information needs having a
More informationHow an author reveals a character SPI:
How an author reveals a character SPI: 0701.8.6 What it looks like on a test. Julie jumped up and down while waiting for her test to be graded. She bit her nails and made loud sighing noises. She knew
More informationCSE 258 Lecture 1.5. Web Mining and Recommender Systems. Supervised learning Regression
CSE 258 Lecture 1.5 Web Mining and Recommender Systems Supervised learning Regression What is supervised learning? Supervised learning is the process of trying to infer from labeled data the underlying
More informationMEETING OF TV YOUTH PROGRAMME EXPERTS. (Ponta Delgada, 12 to 15 November 2005)
ZDF Hear me out! Script with time codes ENGLISH MEETING OF TV YOUTH PROGRAMME EXPERTS Kevin: Hear me out! 10:00:15:00 10:00:49:00 Kevin (on): This is my cat Minka. She is a little runaway. I like animals
More informationArtificial Intelligence: Its Scope and Limits, by James Fetzer, Kluver Academic Publishers, Dordrecht, Boston, London. Artificial Intelligence (AI)
Artificial Intelligence: Its Scope and Limits, by James Fetzer, Kluver Academic Publishers, Dordrecht, Boston, London. Artificial Intelligence (AI) is the study of how to make machines behave intelligently,
More informationComputational Cognitive Neuroscience
Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience *Computer vision, *Pattern recognition, *Classification, *Picking the relevant information
More informationThales Foundation Cyprus P.O. Box 28959, CY2084 Acropolis, Nicosia, Cyprus. Level 3 4
Thales Foundation Cyprus P.O. Box 28959, CY2084 Acropolis, Nicosia, Cyprus Kangourou Linguistics English Competition 2017 Level 3 4 Date: 4 February 2017 Time: 10:00 11:15 Questions 1 10 = 3 points Questions
More informationBBC LEARNING ENGLISH Shakespeare Speaks
BBC LEARNING ENGLISH Shakespeare Speaks I must be cruel, only to be kind: Lesson plan The video to accompany this lesson plan can be found here: http://www.bbc.co.uk/learningenglish/english/course/shakespeare/unit-1/session-20
More informationTopics for today Ethics Bias
HCI and Design Topics for today Ethics Bias What are ethics? The study of moral standards and how they affect conduct Moral standards are A system of principles governing the appropriate conduct of an
More informationBottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering SUPPLEMENTARY MATERIALS 1. Implementation Details 1.1. Bottom-Up Attention Model Our bottom-up attention Faster R-CNN
More informationMEDICAL MALE CIRCUMCISION. A discussion tool
MEDICAL MALE CIRCUMCISION A discussion tool About the MMC Discussion Tool Learn and talk about Medical Male Circumcision with this exciting learning tool. It consists of a 15-minute DVD, which tells the
More informationA Vision-based Affective Computing System. Jieyu Zhao Ningbo University, China
A Vision-based Affective Computing System Jieyu Zhao Ningbo University, China Outline Affective Computing A Dynamic 3D Morphable Model Facial Expression Recognition Probabilistic Graphical Models Some
More informationSelection of Linking Items
Selection of Linking Items Subset of items that maximally reflect the scale information function Denote the scale information as Linear programming solver (in R, lp_solve 5.5) min(y) Subject to θ, θs,
More information