# Towards Self-organizing Personal Knowledge Assistants in Evolving Corporate Memories

arXiv: https://arxiv.org/abs/2308.01732 · HTML: https://mlsanity.com/paper/2308.01732/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 219 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [SDM-RDFizer: An RML Interpreter for the Efficient Creation of RDF Knowledge Graphs](https://mlsanity.com/paper/2008.07176/) (2020)
- [The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users](https://mlsanity.com/paper/1301.7385/) (2013)
- [Creating a Scholarly Knowledge Graph from Survey Article Tables](https://mlsanity.com/paper/2012.00456/) (2020)
- [RocketRML - A NodeJS implementation of a use-case specific RML mapper](https://mlsanity.com/paper/1903.04969/) (2019)
- [Context Spaces as the Cornerstone of a Near-Transparent & Self-Reorganizing Semantic Desktop](https://mlsanity.com/paper/1805.02181/) (2018)
- [Dataset Generation Patterns for Evaluating Knowledge Graph Construction](https://mlsanity.com/paper/2104.13576/) (2021)
- [An Easy & Collaborative RDF Data Entry Method using the Spreadsheet Metaphor](https://mlsanity.com/paper/1804.04175/) (2018)
- [Simplified SPARQL REST API - CRUD on JSON Object Graphs via URI Paths](https://mlsanity.com/paper/1805.01825/) (2018)
- [Deep Linking Desktop Resources](https://mlsanity.com/paper/1805.03491/) (2018)
- [Managed Forgetting to Support Information Management and Knowledge Work](https://mlsanity.com/paper/1811.12155/) (2018)
- [Advanced Memory Buoyancy for Forgetful Information Systems](https://mlsanity.com/paper/1811.12177/) (2018)
- [Inflection-Tolerant Ontology-Based Named Entity Recognition for Real-Time Applications](https://mlsanity.com/paper/1812.02119/) (2018)
- [Interactive Concept Mining on Personal Data -- Bootstrapping Semantic Services](https://mlsanity.com/paper/1903.05872/) (2019)
- [Bridging the Technology Gap Between Industry and Semantic Web: Generating Databases and Server Code From RDF](https://mlsanity.com/paper/2011.07957/) (2020)
- [The Person Index Challenge: Extraction of Persons from Messy, Short Texts](https://mlsanity.com/paper/2011.07990/) (2020)
- [Interactively Constructing Knowledge Graphs from Messy User-Generated Spreadsheets](https://mlsanity.com/paper/2103.03537/) (2021)
- [Mapping Spreadsheets to RDF: Supporting Excel in RML](https://mlsanity.com/paper/2104.13600/) (2021)
- [A Linked Data Application Framework to Enable Rapid Prototyping](https://mlsanity.com/paper/2104.13605/) (2021)
- [Spread2RML: Constructing Knowledge Graphs by Predicting RML Mappings on Messy Spreadsheets](https://mlsanity.com/paper/2110.12829/) (2021)

## Built on by (most cited first, 1 of 1)

- [Data Collection of Real-Life Knowledge Work in Context: The RLKWiC Dataset](https://mlsanity.com/paper/2404.10505/) (2024)

## Abstract (arXiv)

This paper presents a retrospective overview of a decade of research in our department towards self-organizing personal knowledge assistants in evolving corporate memories. Our research is typically inspired by real-world problems and often conducted in interdisciplinary collaborations with research and industry partners. We summarize past experiments and results comprising topics like various ways of knowledge graph construction in corporate and personal settings, Managed Forgetting and (Self-organizing) Context Spaces as a novel approach to Personal Information Management (PIM) and knowledge work support. Past results are complemented by an overview of related work and some of our latest findings not published so far. Last, we give an overview of our related industry use cases including a detailed look into CoMem, a Corporate Memory based on our presented research already in productive use and providing challenges for further research. Many contributions are only first steps in new directions with still a lot of untapped potential, especially with regard to further increasing the automation in PIM and knowledge work support.