Concise Preservation by combining Managed Forgetting and Contextualized Remembering Research Talk, May 9, 2014 University of Twente, Enschede Speaker: Nattiya Kanhabua L3S Research Center / University of Hannover
ForgetIT Project Consortium An interdisciplinary team of experts in: • Preservation, information management, information extraction • Multimedia analysis, storage computing, cognitive psychology
Outline Overview of the ForgetIT project • Motivation • Example use cases Work Package 3: Managed forgetting • Objective • Achievements in Year 1
A Computer that forgets ? Intentionally ?? And in context of preservation??? However, we are facing: • Dramatic increase in content creation (e.g. digital photos) • Increasing use of mobile devices with restricted capacity • Information overload and changing professional + private lives • Inadvertent forgetting in lack of systematic preservation Forgetting plays a crucial role for human remembering and life (focus, stress on important information, forgetting of details) Forget IT Shouldn't there be something like forgetting in digital memories as well?
Motivation Needs increasing amount of Opportunities digital content major progress in handled over decades preservation more or less systematic technology backup maturing Information strategies used extraction non-paper practices for technology Major Obstacles long-term perspective storage as service (e.g. required large gap for adoption clouds) high-up front cost no established practices lack of understanding of benefit reluctance to invest
Opening Enabling Creating alternatives to Vision: Building a Bridge immediate smooth “keep it all” and Easing transition to benefit + “forgetting by interpretation preservation reducing effort accident” in the long run ForgetIT taking inspiration from and complementing human memory Needs increasing amount of Opportunities digital content handled over decades major progress in more or less systematic preservation technology backup strategies used maturing information extraction technology non-paper practices for Major Obstacles long-term perspective storage as service (e.g. large gap for adoption required clouds) high-up front cost no established practices lack of understanding of benefit reluctance to invest
Building the Bridge • bringing back information into active use in a Contextualized meaningful way Remembering Synergetic Preservation Managed Forgetting • couples information • as opposed to the current management and “forgetting by accident” preservation management • inspired by human forgetting
Simple Example: Holidays • Creation of • Changes in • Life goes on • High summary • Pictures go life (e.g. page awareness • Addition of • Trip to marriage) out of focus of trip details • Addition/ • Creation of a • Showing of context info Paris with • Further update of small Friends pictures • Thousands • Sorting out context diverse reduction of information subset for redundancy of pictures redundant • Dealing • Rest of showing pictures • Sub- with occasionally pictures into preservatio archive grouping n issues and sorting February 2015 Paris Team: Me, Mary girlfriend Christine, Tom +20 Years +5-10 Years +1 Years +1 month after trip
Simple Example: Holidays • Creation of • Changes in • Life goes on • High summary • Pictures go life (e.g. page awareness • Addition of • Trip to marriage) out of focus of trip details • Addition/ • Creation of a • Showing of context info Paris with • Further update of small Friends pictures • Thousands • Sorting out context diverse reduction of information subset for redundancy of pictures redundant • Dealing • Rest of showing pictures • Sub- with occasionally pictures into preservatio archive grouping n issues and sorting February 2015 Paris Team: Me, Mary Girlfriend girlfriend Christine, Tom wife +20 Years +5-10 Years +1 Years +1 month after trip
Simple Example: Holidays • Creation of • Changes in • Life goes on • High summary • Pictures go life (e.g. page awareness • Revisiting • Addition of • Trip to marriage) out of focus of trip details of Photo of • Addition/ • Creation of a • Showing of context info Paris with trip photos • Further update of small Friends pictures • Re- • Thousands • Sorting out context diverse reduction of integration information subset for redundancy of pictures redundant into overall • Dealing • Rest of showing pictures photo • Sub- with occasionally pictures into collection preservatio archive grouping (link into n issues and sorting February 2015 context) Paris Team: Me, Mary Girlfriend girlfriend Christine, Tom wife +20 Years +5-10 Years +1 Years +1 month after trip
Managed Forgetting Inspired by central role of human forgetting: decreasing • help in identifying and focus on relevant information memory • support preservation content selection buoyancy • replace inadvertent forgetting Based on: • Careful information value assessment • Forgetting strategies via policies • Forgetting options to integrate final manual checking before deletion • Combination with multi-tier storage solution possible Managed forgetting ≠ automatic deletion Instead: range of forgetting options e.g. • resource condensation • change of indexing & ranking • reduction of redundancy Use of tiers
Contextualized Remembering Aim: Bring back information into active use in a meaningful way even if a lot of time has passed Aim for semantic level of preservation Based on: Take into account relevant parts of context when moving to archive Increase contextualization of preserved content Consider context evolution over time ( evolution-aware contextualization ) A. Ceroni, N. K. Tran, N. Kanhabua and C. Niederée, Bridging Temporal Context Gaps using Time-Aware Re-Contextualization , (To appear) SIGIR’2014
Evolution-aware Contextualization & Re-contextualization Human Forgetting Context of Semantic evolution Change in focus Interpretation Structural evolution Structural changes Terminology evolution C‘‘ C‘‘‘ C‘ C Semantic Evolution Contextualization Detection D D D D Re-contextualization Evolution-aware Information Contextualization System Context-aware Preservation Pres(C‘‘) Archival Information Pres(C‘‘) Pres(C‘) System Pres(D‘) Pres(D‘) Pres(D‘) t
Work Package 3: Managed Forgetting V. Mayer-Schönberger. Delete - The Virtue of Forgetting in the Digital Age . Morgan Kaufmann Publishers, 2009.
Objectives of WP3 and Year 1 Focus WP3 Objectives • Conceptual model for managed forgetting Foundations of human-brain inspired managed forgetting • Development of managed forgetting methods Information value assessment Set of methods for Preserve-or-Forget Policy-driven approach to managed forgetting (Y2) Focus of Year 1 • Conceptual model for managed forgetting • Design and implement the core managed forgetting process • Exploratory research of information value assessment
Role in Preserve-or-Forget Architecture
Achievements in Year 1 Research questions and first ideas for complementing human memory (co-worked with WP2, D3.1) • Episodic memory: reconstruct lifetime memories and support reminiscence • Working memory: better focus in current information use Information value assessment (co-worked with WP9, D3.2) • Data model and a computation method based on Semantic Web technologies • Integration to PIMO semantic desktop and Preserve-or-Forget middleware Exploratory studies (D3.2) • Analyzing collective memory of public events in Wikipedia • Analyzing high-impact features for content retention in the Social Web • Feature selection for efficiency and scalability
Complementing Human Memory: Our First Ideas Goal: understand how to complement human memory processes Focus on two types of memories: • Episodic memory: support reminiscence of long-term autobiographical events • Working memory: better focus in current information use, e.g. de-cluttering personal information spaces Two information values: memory buoyancy , and preservation value
Information Value Assessment Memory buoyancy • Information objects sinking down with decreasing importance, usage , etc. Preservation value • Used to decide which information object will be preserved or archived Memory Buoyancy Preservation Value Short-/Mid-term current interests Long-term need for future use E.g. meeting or travel documents E.g. important life events Subjective metrics Objective metrics + usage logs (views, edits, modifies) + diversity, coverage, quality + time, e.g., aging or recency + social context, external influences
Forgetting in Episodic Memory Rapidly forget details - > “less redundancy” Reconstruct from similar events, context Rely on common patterns - > “false memory” Our first ideas: • Store details differing among similar event types forgotten in human memory • Event-centric organization of digital items can play an important role
Recommend
More recommend
