This repository collects all use cases for CLARIAH-PLUS, across all work packages and interest groups. Our aim is to have a central repository where everybody can get insight into the wide variety of use cases we currently deal with. With this transparency with intend to foster cooperation and provide a basis for discussion and implementation, both in the CLARIAH interest groups and beyond.
At this stage, the structure of the use cases is still very much open-ended, we intend to first gather use cases and in a later stage distill a more structured format.
Everybody working in CLARIAH is welcome and encouraged to contribute his/her use cases. Please see the contribution guidelines and the template.
The below listing links to all use cases based on their state, but in no further particular order, better ordering will be applied at a later stage and is all subject to further discussion as we grow.
| Name | WP | IG | Tech |
|---|---|---|---|
| A Cross-Media Analysis of the Refugee Crisis | 5, 6 | WF,AV,TP | MediaSuite |
| Deep-learning for Dutch text mining | 3 | TP | DeepFrog |
| Historical research across (audio)visual and textual archives and collections | 5 | Ann, WF, Cur | MediaSuite |
| Sex, Beer and RomComs: Studying the Debate on Dutch film | 5, 2, 3, 4, 6 | AV, TP, Ann, LoD, WF, Cur, UI | |
| Stories in Motion: Integrating oral histories into the Media Suite | 5 | AV | MediaSuite |
| Triples-workbench: store, browse, query and visualize triples | 4 | LoD, UI, WF | |
| Key point detection/pose analysis for Eye Jean Desmet collection through DANE | 5 | AV | MediaSuite |
| Name | WP | IG | Tech |
|---|---|---|---|
| Computer vision annotations 'n' enrichments of audiovisual data | 5 | AV,DO,WF | DANE |
| DANS CMDI use case for CLARIAH WP3 | 3 | Prv | CMDI |
| Historical research on media-events across heterogenous broadcast datasets with linked and missing data | 5 | AV,TP,Ann,LoD | MediaSuite |
| Linkage of Dutch Civil Records | 4 | LoD,WF,Cur | LINKS |
| Providing Language and Speech webservices at CLST (Radboud University, Nijmegen) | 3, 2 | DO,TP,WF | CLAM, LaMachine |
| Retrodigitization of Text-critical Editions | 3 | TP,Ann | FoLiA, FLAT |
| Speech transcription of audiovisual data | 5 | AV,Do | Media Suite |
| Vocab Recommender | 4 | LoD,CuR,WF | |
| Tracing Re-use | 5 | WF,AN,AVP | Media Suite |
| Name | WP | IG | Tech |
|---|---|---|---|
| Annotation of spelling correction for CLIN28 Shared Task | 3 | Ann | FLAT |
| Automatic linguistic enrichment for Dutch texts using Frog | 3 | TP | Frog, FoLiA |
| COW:Integrated CSV to RDF converter | 4 | LoD,Cur,WF | COW |
| Data format for linguistically-annotated corpora | 3 | Ann,TP,LoD | FoLiA |
| Extracting Information about Flood Disasters | 3 | Ann | FLAT |
| grlc -> sparql queries as api and with metadata | 4 | LoD | grlc |
| Nederlab: Automatic Linguistic Enrichment of Historical Dutch | 3, 6 | TP,Ann | Frog,FoliA |
| Negation Annotation in Dutch dialogue | 3 | Ann | FLAT |
| PARSEME: Annotation of verbal multi-word expressions | 3 | Ann | FoLiA |
| PICCL deployment at a CLARIN centre | 3 | DO | LaMachine |
| Quickly building webservices with CLAM | 3, 2 | DO,WF,TP | CLAM |
| Research Environment for Workshop: Cataloguing of Textual Cultural Heritage Objects | 3 | DO,TP | LaMachine |
| Syntactic Movement Annotation | 3 | Ann | FLAT |
| Tools to the data: Text Mining for Health Inspection | 3 | DO,TP | LaMachine, Frog |
- Ann = Annotation
- AV = Text Processing
- Cur = Curation
- DO = DevOps
- LoD = Linked Open Data
- TP = Text Processing
- Prv = Preservating
- UI = UI/UX
- WF = Workflows
The technology column refers to the most prominent CLARIAH products that feature in the use case (keep it short):
- CLAM - A framework to quickly build RESTful webservices and have a generic web-UI
- CMDI - CLARIN's Component Metadata Infrastructure
- COW - CSV to RDF converter (CSVW)
- DANE - Handles compute task assignment and file storage for the automatic annotation of content.
- DeepFrog - Deep-learning NLP tool & models for Dutch
- FLAT - A web-based annotation tool for (linguistic) annotation of text documents
- FoLiA - An XML-based Format for Linguistic Annotation
- Frog - An NLP-suite for Dutch
- grlc - converts your SPARQL queries into RESTful APIs.
- LINKS - Command line tool for linking civil registries
- LaMachine - A meta-distribution with various NLP/CLARIAH tools and services
- MediaSuite - A research environment to search, analyse, and annotate media collections.