KI-Startseite

Weitere Themen
KI-Interessierte auf DIN.ONE

1. Assertional Knowledge Engineering

1.1. Information Extraction

Contributors:

  • Diego Collarana (FIT)
  • Sven Hertling (FIZ), Harld Sack (FIZ), Heike Fliegl (FIZ)
  • Desiree Heim (DFKI)
  • Markus Schröder (DFKI)
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ...

Short definition/description of this topic: please fill in ...

  • From NLP community: relation extraction
  • closed IE vs open IE
  • related survey: https://arxiv.org/abs/2312.17617
  • related approach: https://aclanthology.org/2024.findings-acl.839/
  • extract structural knowledge from natural language texts.
  • typical: Named Entity Recognition (NER), Relation Extraction (RE) and Event Extraction (EE) 
  • References: Derong Xu, Wei Chen, Wenjun Peng, Chao Zhang, Tong Xu, Xiangyu Zhao, Xian Wu, Yefeng Zheng, and Enhong Chen. Large language models for generative information extraction: A survey. CoRR, abs/2312.17617, 2023
  • Content ... 
  • Content ...
  • Content ...

1.1.1. KG Completion (A-Box)

Short definition/description of the topic: please fill in ...

  • Content ...

1.1.1.1. Link Prediction

Short definition/description of the topic: please fill in ...

  • Content ...

1.1.1.2. Relation Prediction

Short definition/description of the topic: please fill in ...

  • Content ...

1.1.1.3. Fact Checking / Triple Testing

Short definition/description of the topic: please fill in ...

  • Content ...

1.1.1.4. Literal Completion (labels/comments/descriptions)

Short definition/description of the topic: please fill in ...

  • Content ...

1.2. Entity Linking (between KGs)

  • Definition/description: Given two entity representations as text (verbalized or in RDF serialization), ask LLM if the entities are referring to the same real-world entity.
  • candidate generation can be done via Sentence BERT models

Markus Schröder 

  • typical: mapping mentions to their corresponding entities given a context
  • between KGs: ... ?
  • also embedding based entity linking, more general: "Neural entity linking"
  • LLM: good for interpreting uncommon mention
  • References: Ozge Sevgili, Artem Shelmanov, Mikhail Y. Arkhipov, Alexander Panchenko, and Chris
    Biemann. Neural entity linking: A survey of models based on deep learning. Semantic Web, 13(3):527–570, 2022

Contributors:

  • Sven Hertling (FIZ), Harald Sack (FIZ), Heike Fliegl (FIZ)
  • Desiree Heim (DFKI)
  • Markus Schröder (DFKI)
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

1.3. Entity Disambiguation

Desiree Heim Markus Schröder 

  • Definition/Description: Disambiguation: given mentions and contexts, need a function which maps them to entities in KG
  • Oftentimes also part of IE pipelines (e.g. KG Completion)
  • has typical steps: candidate generation, entity ranking
  • Direct LLM assistance: Verbalized description of link candidates compared against a text snippet that contains the entity that should be linked/disambiguated + formulated as a classification task
  • Indirect LLM assistance: E.g., using LLM-assisted KG IE from texts and compare the found entities and relationships against the neighborhood of the link candidates
  • References: https://doi.org/10.48550/arXiv.2406.11400; https://doi.org/10.2991/978-94-6463-264-4_79

Contributors:

  • Desiree Heim (DFKI)
  • Markus Schröder (DFKI)
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

2. Terminological Knowledge Engineering

2.1. Ontology Design

Contributors:

  • Sven Hertling (FIZ), Harald Sack (FIZ), Heike Fliegl (FIZ)
  • Michael Wetzel (Coreon)
  • Sabine Mahr (word b sign)
  • ... 

Short definition/description of the topic: please fill in ...

2.1.1. Competency Question (CQ) Generation

Short definition/description of the topic: the process of formulating questions that serve as a benchmark to assess the completeness and adequacy of an ontology

2.1.2. User Stories / Personas Generation

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

2.1.3. Ontology Learning (Automated ontology design from text)

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

2.2. Ontology Evaluation

Contributors:

  • Sven Hertling (FIZ), Harald Sack (FIZ), Heike Fliegl (FIZ)
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

2.2.1. Competency Question (CQ) generation (from given ontologies)

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

2.2.2. CQ to SPARQL

Short definition/description of the topic: Given a competency question, formulate a SPARQL query to check if the question could be solved.

  • Content ...
  • Content ...
  • Content ...

2.3. Ontology Mapping

Contributors:

  • Sven Hertling (FIZ), Harald Sack (FIZ), Heike Fliegl (FIZ)
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

Short definition/description of the topic: please fill in ...

2.4. Ontology Documentation

Contributors:

  • Daniel Baldassare (doctima)
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

Definition/Description: please fill in ...

Draft from Daniel Baldassare :

  • Data model description: nodes and relationships classes
  • Metadata model description: nodes and relationships' s metadata (identifiers, optional and required metadata)
  • Use with LLM:
    • How to use it for standard RAG ( which embedding model)
    • How to use it for GraphRAG/semantic layer (which embedding model, which additional metadata)

2.4.1. Class and Relation Descriptions/Labels

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

3. Reasoning

3.1. Approx/Probabilistic Reasoning via LLMs (LLM supported)

Contributors:

  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

3.2. Constraint Checking

Contributors:

  • Robert David
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

3.3. Data Repairs (→ maybe move to completion?)

Contributors:

  • Robert David
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ... 

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

4. Downstream Tasks

4.1. KG/Ontology Embeddings

Contributors:

  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • Please add yourself if you want to contribute ...
  • ...

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

4.2. Please add other Downstream Tasks ...

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

4.3. Please add other Downstream Tasks ...

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

4.4. Please add other Downstream Tasks ...

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...

5. User Interface / Access

5.1. Natural Language Interface to KG

  • Natural Language to SPARQL

Desiree Heim 

  • Definition/Description: 
  • Text2QueryLanguage (e.g. Text2SPARQL)
    • Direct translation of user queries into equivalent knowledge graph query languages by prompting an LLM
    • The knowledge graph structure can be given either by including a (sub)schema or a subgraph in the query translation prompt
  • KG-RAG
    • Can be done by extracting knowledge graph entities and potentially relevant relationships from the user query and retrieving relevant triples from the knowledge graph which are given as a context to the prompt containing the user query
  • References:https://doi.org/10.48550/arXiv.2407.01409, https://ceur-ws.org/Vol-3592/paper6.pdf

Contributors:

  • Diego Collarana (FIT)
  • Sven Hertling (FIZ), Harld Sack (FIZ), Heike Fliegl (FIZ)
  • Desiree Heim (DFKI)
  • Markus Schröder (DFKI)
  • Sabine Mahr (word b sign)
  • Please add yourself if you want to contribute ...
  • ... 

5.2. KG to Natural Language (verbalization)

  • Short definition/description of the topic: please fill in ...

    • Content ...
    • Content ...
    • Content ...
  • OWL constructs to natural language (usually deterministic and no LLM involved?)

Desiree Heim 

  • Typically triple-based verbalization
  • Different granularity of verbalizations (very exact subject/predicate/object sentences vs summary of subgraphs)
  • ABOX statement verbalization: Often employed in RAG-based KGQA processes 
  • TBOX statement verbalization: Relevant for Text2QueryLanguage, Ontology-based KG Completion tasks 
  • References: https://doi.org/10.48550/arXiv.2402.01495; https://doi.org/10.1145/3587259.3627571

Contributors:

  • Daniel Baldassare (doctima)
  • Sven Hertling (FIZ), Harald Sack (FIZ), Heike Fliegl (FIZ)
  • Desiree Heim (DFKI)
  • Markus Schröder (DFKI)
  • Sabine Mahr (word b sign)
  • ... 

5.3. Multilingual Translation of Literals

Contributors:

  • Michael Wetzel (Coreon)
  • Sabine Mahr (word b sign)
  • Please add yourself if you want to contribute ...
  • ... 

Short definition/description of the topic: please fill in ...

  • Content ...
  • Content ...
  • Content ...
  • No labels