ODISSEI portal
This repository is used for setting up the front-end of portal.odissei.nl and skosmos.odissei.nl.
Result filters
Resource type
- Web service (4)
- Library (1)
- Web application (1)
Type of tool
- Text processing (8)
- Enriching (3)
- Machine learning (3)
- Multimedia processing (3)
- Browsing (2)
- Exploration (2)
- Information retrieval (2)
- Archiving (1)
Tool task
- Annotation (20)
- Tagging (8)
- POS tagging (5)
- Structural analysis (5)
- Dependency parsing (4)
- Lemmatisation (4)
- Parsing (4)
- Named entity recognition (3)
Field of study
- Linguistics (22)
- Computational linguistics (12)
- Philology (12)
- Textual and content analysis (11)
- Humanities (8)
- Textual and linguistic corpora (8)
- Sociology (5)
- Structural Analysis (5)
Availability
- Attribution (6)
- Public (6)
Organisation
Keywords
- nlp (29)
- natural language processing (16)
- annotation (12)
- linguistics (12)
- dutch (10)
- rdf (9)
- text-processing (8)
- folia (7)
Loading...
119 record(s) found
Search results
-
-
ODISSEI portal back-end
Orchestrator for all ODISSEI-related ingestion workflows. -
ODISSEI Knowledge Graph
This repository contains the software we used to extract, transform and load (ETL) data into the platform kg.odissei.nl. If you are mainly interested in the resulting data, feel free to ignore this repository and go to this platform directly. -
Odissei Code Library
The ODISSEI code library is a collection of code and scripts used to execute projects using the ODISSEI infrastructure. ODISSEI (Open Data Infrastructure for Social Science and Economic Innovations) is the national research infrastructure for the social sciences in the Netherlands. ODISSEI brings together researchers with the necessary data, expertise and resources to conduct ground-breaking research and embrace the computational turn in social enquiry. Through ODISSEI, researchers have access to large-scale, longitudinal data collections as well as innovative and diverse new forms of data. These can be linked to administrative data at Statistics Netherlands (CBS). Combining data from a wide range of sources enables researchers to answer new, exciting, interdisciplinary research questions and to investigate existing questions in novel, new ways. -
GrETEL
Search engine for the exploitation of syntactically annotated corpora or treebanks -
stam
Stand-off Text Annotation Model (STAM) is a data model for stand-off-text annotation where any information on a text is represented as an annotation. This repository contains the model's full specification, extensions, schemas, examples and documentation. -
asrservice
An Automatic Speech Recognition Service for a variety of languages, powered by WhisperX -
foliadocserve
The FoLiA Document Server is a backend HTTP service to interact with documents in the FoLiA format, a rich XML-based format for linguistic annotation (http://proycon.github.io/folia). It provides an interface to efficiently edit FoLiA documents through the FoLiA Query Language (FQL). -
PaQu
Met PaQu (Parse & Query) kun je zoeken in syntactisch geannoteerde Nederlandstalige corpora. PaQu ondersteunt twee manieren van zoeken. Met de eerste, eenvoudige, manier kun je naar woordparen zoeken, met daarbij eventueel hun syntactische relatie. De tweede, ingewikkeldere, manier gebruikt de zoektaal XPath. In PaQu is een aantal syntactisch geannoteerde corpora standaard beschikbaar. Maar het is ook mogelijk om je eigen teksten aan te bieden. Deze teksten worden dan door de automatische ontleder geanalyseerd, en opgeslagen. Vervolgens kun je dan op dezelfde manier in je eigen teksten zoeken. -
GaLAHaD Train Battery
Python program for training linguistic annotation taggers based on a configuration file and list of datasets. It prepares the resulting trained models for dockerization and adds relevant metadata. It is tagger software agnostic as long as a simple python shell is built around it.