CIKM 2015 Melbourne Australia Oct. 22, 2015 Building a Better Connected World with Data Mining and Artificial Intelligence Technologies



Similar documents
Learning to Process Natural Language in Big Data Environment

Steven C.H. Hoi School of Information Systems Singapore Management University

Applications of Deep Learning to the GEOINT mission. June 2015

Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15

User Modeling in Big Data. Qiang Yang, Huawei Noah s Ark Lab and Hong Kong University of Science and Technology 杨 强, 华 为 诺 亚 方 舟 实 验 室, 香 港 科 大

The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2

A picture is worth five captions

Search Result Optimization using Annotators

Core Curriculum to the Course:

Deep Learning For Text Processing

Doing Multidisciplinary Research in Data Science

Automatic Mining of Internet Translation Reference Knowledge Based on Multiple Search Engines

Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection

AnalysisofData MiningClassificationwithDecisiontreeTechnique

Convolutional Feature Maps

Network Machine Learning Research Group. Intended status: Informational October 19, 2015 Expires: April 21, 2016

Deep learning applications and challenges in big data analytics

PhD in Computer Science and Engineering Bologna, April Machine Learning. Marco Lippi. Marco Lippi Machine Learning 1 / 80

Recognition. Sanja Fidler CSC420: Intro to Image Understanding 1 / 28

RESEARCH ON THE FRAMEWORK OF SPATIO-TEMPORAL DATA WAREHOUSE

Eastern Washington University Department of Computer Science. Questionnaire for Prospective Masters in Computer Science Students

Tech Presentation 2016

Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network

A1 Introduction to Data exploration and Machine Learning

Sense Making in an IOT World: Sensor Data Analysis with Deep Learning

A Framework-based Online Question Answering System. Oliver Scheuer, Dan Shen, Dietrich Klakow

How To Use Neural Networks In Data Mining

Gated Neural Networks for Targeted Sentiment Analysis

Big Data and Scripting. (lecture, computer science, bachelor/master/phd)

Microblog Sentiment Analysis with Emoticon Space Model

Recurrent Neural Networks

CS4025: Pragmatics. Resolving referring Expressions Interpreting intention in dialogue Conversational Implicature

CoolaData Predictive Analytics

How To Make Sense Of Data With Altilia

Prerequisites. Course Outline

Semester Review. CSC 301, Fall 2015

Why is Internal Audit so Hard?

The Need for Training in Big Data: Experiences and Case Studies

Matrix Logic WirelessDMS Service 2.0

An Introduction to Data Mining

International Journal of Scientific & Engineering Research, Volume 4, Issue 11, November ISSN

Natural Language to Relational Query by Using Parsing Compiler

INFORMATION TECHNOLOGY (IT) 515

David G. Belanger, PhD, Senior Research Fellow, Stevens Institute of Technology, New Jersey, USA Topic: Big Data - The Next Phase Abstract

Artificial Intelligence for ICT Innovation

COURSE TITLE COURSE DESCRIPTION

Professional Organization Checklist for the Computer Science Curriculum Updates. Association of Computing Machinery Computing Curricula 2008

The Combination Forecasting Model of Auto Sales Based on Seasonal Index and RBF Neural Network

Taking Inverse Graphics Seriously

Module Catalogue for the Bachelor Program in Computational Linguistics at the University of Heidelberg

Intelligent Database Monitoring System using ARM9 with QR Code

School District of Springfield Township

Domain Name Abuse Detection. Liming Wang

Augmented Search for Web Applications. New frontier in big log data analysis and application intelligence

IEEE International Conference on Computing, Analytics and Security Trends CAST-2016 (19 21 December, 2016) Call for Paper

Data, Measurements, Features

8. Machine Learning Applied Artificial Intelligence

Data Mining Techniques

Introduction to Data Mining

A NEW DECISION TREE METHOD FOR DATA MINING IN MEDICINE

Fall 2012 Q530. Programming for Cognitive Science

Network Big Data: Facing and Tackling the Complexities Xiaolong Jin

Chapter 1. Dr. Chris Irwin Davis Phone: (972) Office: ECSS CS-4337 Organization of Programming Languages

Machine Learning CS Lecture 01. Razvan C. Bunescu School of Electrical Engineering and Computer Science

Latent variable and deep modeling with Gaussian processes; application to system identification. Andreas Damianou

Software Development Training Camp 1 (0-3) Prerequisite : Program development skill enhancement camp, at least 48 person-hours.

Mobile Phone APP Software Browsing Behavior using Clustering Analysis

A Framework for Personalized Healthcare Service Recommendation

EVILSEED: A Guided Approach to Finding Malicious Web Pages

How To Prevent Network Attacks

Clustering Big Data. Anil K. Jain. (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012

TDWI Best Practice BI & DW Predictive Analytics & Data Mining

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence

MEng, BSc Applied Computer Science

Masters in Information Technology

Automatic Knowledge Base Construction Systems. Dr. Daisy Zhe Wang CISE Department University of Florida September 3th 2014

THE DO S AND DON TS OF WEB CHAT. with Johan Jacobs

Healthcare data analytics. Da-Wei Wang Institute of Information Science

Big-Data Computing with Smart Clouds and IoT Sensing

An Introduction to Deep Learning

Mining Signatures in Healthcare Data Based on Event Sequences and its Applications

CS Master Level Courses and Areas COURSE DESCRIPTIONS. CSCI 521 Real-Time Systems. CSCI 522 High Performance Computing

Data Mining and Exploration. Data Mining and Exploration: Introduction. Relationships between courses. Overview. Course Introduction

Data Mining for Customer Service Support. Senioritis Seminar Presentation Megan Boice Jay Carter Nick Linke KC Tobin

Active Learning SVM for Blogs recommendation

Dan French Founder & CEO, Consider Solutions

Image Search by MapReduce

What to Mine from Big Data? Hang Li Noah s Ark Lab Huawei Technologies

Transcription:

CIKM 2015 Melbourne Australia Oct. 22, 2015 Building a Better Connected World with Data Mining and Artificial Intelligence Technologies Hang Li Noah s Ark Lab Huawei Technologies

We want to build Intelligent Mobile Devices Data Mining & Artificial Intelligence Intelligent Telecommunication Networks Intelligent Enterprise

Intelligent Telecommunication Networks Software-defined Network Network Maintenance Network Planning and Optimization

Intelligent Enterprise Supply Chain Management Customer Relationship Management Human Resources Management Information and Knowledge Management Communication

Intelligent Mobile Devices Information Recommendation Information Extraction Personal Information Management Machine Translation Natural Language Dialogue(Question Answering)

This Talk: Natural Language Dialogue

Demo: Neural Responding Machine

Outline Information Access through Natural Language Dialogue Data-Driven Approach Single Turn Dialogue Sentence Representation Learning Our Approach Using Deep Learning Summary

New Paradigm in Information Retrieval? Library Search Web Search Natural Language Dialogue 1970 1990 2010

Information Access through Natural Language Dialogue Multi-turn dialogue Goal: task completion, mostly information access Evaluation: completion / cost Including traditional search and question answering as special cases

Example One: Hotel Booking on Smartphone P: How may I help you? U: I'd like to book a hotel room for tomorrow. P: For how many people? U: Just me. What is the total cost? P: That would be $120 per night. U: No problem. Book the room for one night, please.

Example Two: Auto Call Center U: hello H: hello, how can I help you? U: can you tell me how to find ABC software? H: please go to this URL to download U: how to activate the software? H: please see this document

Academic research Related Work Rule-based approach, e.g., Eliza System, Weizenbaum 1964 Reinforcement learning based approach, e.g., Singh et al 1999 Machine translation based approach, e.g., Ritter et al 2011 Commercial products Apple Siri Google Now MS Cortana

Outline Information Access through Natural Language Dialogue Data-Driven Approach Single Turn Dialogue Sentence Representation Learning Our Approach Using Deep Learning Summary

Data-Driven Approach to Dialogue Will you attend ECML/PKDD 2015? Yes, I will Learning how to converse mainly from data

Data-Driven Approach Key Points Mainly learning from data Avoid difficult language understanding problem as much as possible Fundamental mechanism is simple Issues to Investigate Single-turn dialogue Multi -turn dialogue Knowledge utilization and reasoning (lightweight) Dialogue management (lightweight)

As Scientific Research Problem Not as engineering hacks Scientific methodology Mathematical modeling Result should be reproducible (positivism) Divide and conquer (reductionism)

Outline Information Access through Natural Language Dialogue Data-Driven Approach Single Turn Dialogue Sentence Representation Learning Our Approach Using Deep Learning Summary

Reducing Multi-Turn Dialogue to Single- Turn Dialogue hello U: hello H: hello, how can I help you? U: can you tell me how to find ABC software? H: please go to this URL to download U: how to activate the software? H: please see this document Breaking down multi-turn dialogues to many single-turn dialogues hello, how can I help you can you tell me how to find ABC software? please go to this URL to download how to activate the software? please see this document

Retrieval-based Single Turn Dialogue Repository of Message Response Pairs Retrieval System Learning System

Generation-based Single Turn Dialogue Generation System Learning System

Retrieval-based approach to single turn dialogue 5 million Chinese Weibo data, 1 million Japanese Twitter data Registration deadline: Oct 31, 2015

Outline Information Access through Natural Language Dialogue Data-Driven Approach Single Turn Dialogue Sentence Representation Learning Our Approach Using Deep Learning

Representation of Word Meaning dog cat puppy kitten Using high-dimensional real-valued vectors to represent the meaning of words

Representation of Sentence Meaning New finding: This is possible Mary is loved by John Mary loves John John loves Mary Using high-dimensional real-valued vectors to represent the meaning of sentences

Recent Breakthrough in Natural Language Processing Representations from words to sentences Compositional Representing syntax, semantics, even pragmatics

How Is Learning of Sentence Meaning Possible? Deep neural networks (complicated non-linear models) Big Data Task-oriented Error-reduction and gradient-based

Deep Learning Tools for Learning Sentence Representations Neural Word Embedding Recurrent Neural Networks Recursive Neural Networks Convolutional Neural Networks

Word Representation: Neural Word Embedding M c1 c2 c3 c4 c5 w 1 w 2 w 3 10 1 5 2 1 2.5 1 log P( w, c) P( w) P( c) W T M WC t1 t2 t3 matrix factorization w 1 w 2 w 3 7 1 1 2 3 1 1.5 2 word embedding or word2vec

Recurrent Neural Network (RNN) (Mikolov et al. 2010) On sequence of words Variable length Long dependency: LSTM or GRU the cat sat on the mat h t 1 h t f ( ht 1, xt ) the cat sat. mat x t

Recursive Neural Network (RNN) (Socher et al. 2013) On parse tree of sentence Learning is based on max margin parsing the cat sat on the mat the cat sat on the mat

Convolutional Neural Network (CNN) (Hu et al. 2014) Concatenation the cat sat on the mat the cat sat on sat on the mat Robust parsing Shared parameter on same level Fixed length, zero padding the cat sat on the mat max pooling the cat cat sat sat on on the cat sat sat on on the the mat the cat sat cat sat on sat on the on the mat convolution the cat sat on the mat

Outline Information Access through Natural Language Dialogue Data-Driven Approach Single Turn Dialogue Sentence Representation Learning Our Approach Using Deep Learning Summary

Our Models for Single-Turn Dialogue Using Deep Learning Retrieval-based Deep Match CNN (Hu et al., NIPS 2014) Deep Match Tree (Wang et al., IJCAI 2015) Generation-based Neural Responding Machine (Shang et al., ACL 2015)

DL for NLP @Noah Lab Researchers Zhengdong Lu Lifeng Shang Lin Ma Zhaopeng Tu Interns Baotian Hu Fandong Meng Mingxuan Wang Han Zhao

Natural Language Dialogue System - Retrieval based Approach message retrieved messages and responses matched responses ranked responses online retrieval matching ranking best response offline index of messages and responses matching models ranking model

Deep Match CNN - Archtecture I First represent two sentences, and then match 38

Deep Match CNN - Architecture II Represent and match two sentences simultaneously Two dimensional convolution and pooling 39

Deep Match Tree Constructing deep neural network, with first layer corresponding mined patterns 40

Retrieval based Approach: Accuracy = 70% 上 海 今 天 好 熱, 堪 比 新 加 坡 上 海 今 天 热 的 不 一 般 想 去 武 当 山 有 想 同 游 的 么? 我 想 跟 帅 哥 同 游 ~ 哈 哈 It is very hot in Shanghai today, just like Singapore. It is unusually hot. I want to go to Mountain Wudang, it there anybody going together with me? Haha, I want to go with you, handsome boy Using 5 million Weibo Data

Natural Language Dialogue System - Generation based Approach Response y x y 1 Decoder c Encoder x 1 y x 2 2 Context Generator h y t x T Encoding messages to intermediate representations Decoding intermediate representations to responses Recurrent Neural Network (RNN) Message

Neural Responding Machine Intuitively, a big language model generating responses conditioned on messages Decoder 用 了 Global Encoder Context Generator 都 说??? Attention Signal 华 为 手 机 怎 么 样 Local Encoder 140 million parameters Trained from 5 million Weibo data

Generation based Approach Accuracy = 76% 占 中 终 于 结 束 了 Occupy Central is finally over. 下 一 个 是 陆 家 嘴 吧? 我 想 买 三 星 手 机 Will Lujiazui (finance district in Shanghai) be the next? I want to buy a Samsung phone 还 是 支 持 一 下 国 产 的 吧 Let us support our national brands vs. Accuracy of translation approach = 26% Accuracy of retrieval based approach = 70%

Outline Information Access through Natural Language Dialogue Data-Driven Approach Single Turn Dialogue Sentence Representation Learning Our Approach Using Deep Learning Summary

Take-away Messages Natural language dialogue = new paradigm for information retrieval Data-driven approach is key Current focus is single turn dialogue Sentence representation learning is possible Significant progress being made on single-turn dialogue with deep learning and big data Many interesting and challenging problems to be tackled

Thank you!