Responsive Information Architect Responsive Information Architect - PowerPoint PPT Presentation

Responsive Information Architect Responsive Information Architect Context- -Sensitive Information Seeking Sensitive Information Seeking Context Zhen Wen Zhen Wen In collaboration with Vikram Vikram Aggarwal Aggarwal, Keith Houck, , Keith Houck, Shimei Shimei Pan, Pan, In collaboration with James Shaw, and Michelle Zhou Michelle Zhou James Shaw, and Dept. of Intelligent Multimedia Interaction Dept. of Intelligent Multimedia Interaction IBM T. J. Watson IBM T. J. Watson http://www.research.ibm.com www.research.ibm.com/RIA /RIA http://

Input Challenges Input Challenges Systems often have limited capability of Systems often have limited capability of understanding user inputs understanding user inputs 1440 Broadway, NYC Train stations within 10 blocks 1440 Broadway, NYC Train stations within 10 blocks Crown Plaza at UN 2

Output Challenges Output Challenges One- -size size- -fits fits- -all output is context all output is context- - One insensitive insensitive “hotels hotels” ” “ Family vacation planner Family vacation planner room type room type child- -care facilities care facilities… … child Honeymooner Honeymooner room services room services luxury amenities luxury amenities Conference planner Conference planner business amenities business amenities capacities capacities 3 location . . . location . . .

Output Challenges Output Challenges Fragmented output is ineffective Fragmented output is ineffective 1440 Broadway, NYC Restaurants within 10 blocks 1440 Broadway, NYC Restaurants within 10 blocks 4

What Went Wrong What Went Wrong Request Response Request Response Querying Results Querying Results Data management / search engines Data management / search engines 5 Structured Data Structured Data Text Docs Images/Videos Text Docs Images/Videos

Our Approach Our Approach Exploit user interaction context to improve user Exploit user interaction context to improve user information- -seeking experience seeking experience information Request Response Request Response Responsive Information Architect (RIA) Responsive Information Architect (RIA) Context- Context -sensitive sensitive Context Context- -tailored tailored Input Interpretation Response Creation Input Interpretation Response Creation Conversation Data User Environment Query Results Query Results Data management / search engines Data management / search engines 6 Structured Data Structured Data Text Docs Images/Videos Text Docs Images/Videos

RIA Demo RIA Demo • Real-estate application − Exhibit the difficult problem of info-seeking • Hospitality application − Demonstrate RIA reusability 7

RIA Key Technologies RIA Key Technologies Request Response Request Response Context-driven Context-tailored Input Interpretation Presentation Context Management Context Management Conversation Data User Environment Conversation Data User Environment 8 Data Management Data Management

RIA Key Technologies RIA Key Technologies Request Response Request Response Context-driven Context-tailored Input Interpretation Presentation Context Management Context Management Conversation Data User Environment Conversation Data User Environment 9 Data Management Data Management

Context- -Sensitive Interpretation Sensitive Interpretation – – Context Using Language Cues Using Language Cues Previous query: colonial homes Previous query: colonial homes just those near IBM Hawthorne just those near IBM Hawthorne 1. term segmentation term segmentation 1. 10

An Example: Context- -Sensitive Sensitive An Example: Context Interpretation Interpretation 2. semantic labeling labeling 2. semantic Previous query: colonial homes Previous query: colonial homes just those near IBM Hawthorne Ref op = ‘<=’ Constraint 1: Constraint 2: val = “1” companyName = ‘IBM’ companyLoc = ‘Hawthorne’ stationName = ‘Hawthorne’ cityName = ‘Hawthorne’ 3. use context to attach 3. use context to attach different pieces different pieces Ref Ref near Train Train House Company City House Company City Station Station located-in Constraint: Constraint: 11 Constraint 1 Constraint 2 Constraint 1 Constraint 2 style = ‘colonial’ style = ‘colonial’

However… … However User expressions User expressions System System capability capability System interpretation capability System interpretation capability is/will always be limited is/will always be limited • Diverse expressions for the same thing • Diverse expressions for the same thing 1. Pull that house off my favorite list 1. Pull that house off my favorite list 2. Delete this house 2. Delete this house 3. I’ ’d like to remove the green one here d like to remove the green one here 3. I • Fuzzy expressions • Fuzzy expressions 1. Show me houses in good good school district school district 1. Show me houses in 2. 2. Find me Find me cheap cheap hotels hotels • Concepts/expressions unknown to systems • Concepts/expressions unknown to systems 1. Show houses with fences fences 1. Show houses with 2. I am new here and I work in Hawthorne. I would like to find 2. I am new here and I work in Hawthorne. I would like to find houses close to my company houses close to my company 12

Adaptive Interpretation Adaptive Interpretation 1. Teach users to adapt to system capability 1. Teach users to adapt to system capability – Map user inputs to valid system Map user inputs to valid system- -acceptable inputs acceptable inputs – in context in context q1 q1 q2 q2 U U S S q q 13

Adaptive Interpretation: Our Adaptive Interpretation: Our Approach Approach 1. Teach users to adapt to system capability 1. Teach users to adapt to system capability – Map user inputs to valid system Map user inputs to valid system- -acceptable inputs acceptable inputs – in context in context 2. Teach system to adapt to new user inputs 2. Teach system to adapt to new user inputs – Extend system capability Extend system capability – q1 q1 q2 q2 U U S S q q 14

An Example: User Adaptation An Example: User Adaptation q : Show : Show tudor tudor houses in houses in good good school districts school districts q q ’ ’: Show : Show tudor tudor houses in school districts with over houses in school districts with over q 95% of students attending college 95% of students attending college Store Store 15 q , q ’ ’ > < q , q > <

Our Key Technologies Our Key Technologies Request Response Request Response Context-driven Context-tailored Input Interpretation Presentation Context Management Context Management Conversation Data User Environment Conversation Data User Environment 16 Data Management Data Management

Output Creation Output Creation Automatically create system output tailored to a Automatically create system output tailored to a given user request in context given user request in context 4+ bedrm 4+ bedrm, 2+ bath , 2+ bath colonials in cities in the colonials in cities in the north along Hudson north along Hudson I found 9 houses satisfying your criteria I found 9 houses satisfying your criteria Technical challenges Technical challenges 1. Decide output content and form at run time Decide output content and form at run time 1. 2. Update system output incrementally Update system output incrementally 2. 17

Output Creation Output Creation Automatically create system output tailored to a Automatically create system output tailored to a given user request in context given user request in context 4+ bedrm 4+ bedrm, 2+ bath , 2+ bath colonials in cities in the colonials in cities in the north along Hudson north along Hudson I found 9 houses satisfying your criteria I found 9 houses satisfying your criteria Technical challenges Technical challenges 1. Decide output content and form at run time Decide output content and form at run time 1. 2. Update system output incrementally Update system output incrementally 2. 18

Examples: Environment Relevant Examples: Environment Relevant Find houses in Chappaqua (16) (16) Find houses in Chappaqua Desktop w/o graphics Desktop w/o graphics PDA PDA 19

RIA Summary RIA Summary Enable a context- -sensitive interaction paradigm to sensitive interaction paradigm to Enable a context assist users in info- -seeking seeking assist users in info Understand user inputs in context Understand user inputs in context Provide tailored information presentation in context Provide tailored information presentation in context 20

Ongoing & Future Work Ongoing & Future Work • Extend to unstructured information Extend to unstructured information • – Text docs, images/videos Text docs, images/videos – • Extend information seeking to Extend information seeking to • information analysis information analysis – Leverage data summarization, mining Leverage data summarization, mining – techniques in context techniques in context 21