OER·harvester

Competency catalogue

The 104 active T2.3 competencies: the vocabulary the harvester searches with, the descriptor the alignment reads, and what the alignment found. Compose a harvest →

What the alignment foundHow often each was searched

How many resources the alignment reads as contributing to each competency or developing it: decided at level 2 or 3, or not decided yet and more likely than not to reach 2. 54 competencies have none, 24 one or two. Every figure is a lower bound: on a sample graded on every competency, the map counts 33% of what was graded 2 or 3, and almost nothing of the 5 competencies underlined with dots.

How many times a harvest has searched for each competency, once for each source it asked. 101 competencies have never been searched. A search is not material found: the aligned view says what came of it.

none 1–2 3–9 10–29 30+
never 1–2 3–5 6–11 12+
DDigital 94212203420012149086012303134 GGreen 0000000102000010000100010 RResilience & Entrepreneurial 004000000000000010000120000 TDeep Tech 72643202372825212335201140010

T03 Deep Tech · Skill · Advanced

NLP Engineering

Develop and fine-tune NLP models and applications

Alignment

6 resources likely to contribute to it or develop it

0 decided at level 2 or 3 · 6 not decided yet, more likely than not

On a graded sample, 3 pairs were graded 2 or 3 for it, and the map counts 1.

Retrieval

0 resources harvested by searching its terms

Never searched yet.

Search vocabulary

Domain group
NLP engineeringnatural language processinglanguage model fine-tuningtext processing pipelinenamed entity recognitionsequence labellingsequence labelinginformation extractiontext classificationsentiment analysismachine translationquestion answeringlanguage generationlanguage application development

Zenodo and arXiv take the whole group in one query. GitHub takes one phrase at a time and works left to right, stopping once the competency is satisfied — so on that lane this order decides which terms actually run.

The compiled queries
zenodo ("artificial intelligence" OR "machine learning" OR "generative AI" OR "deep learning" OR "reinforcement learning" OR "large language model" OR "AI") AND ("NLP engineering" OR "natural language processing" OR "language model fine-tuning" OR "text processing pipeline" OR "named entity recognition" OR "sequence labelling" OR "sequence labeling" OR "information extraction" OR "text classification" OR "sentiment analysis" OR "machine translation" OR "question answering" OR "language generation" OR "language application development")
arxiv (all:"artificial intelligence" OR all:"machine learning" OR all:"generative AI" OR all:"deep learning" OR all:"reinforcement learning" OR all:"large language model") AND (all:"NLP engineering" OR all:"natural language processing" OR all:"language model fine-tuning" OR all:"text processing pipeline" OR all:"named entity recognition" OR all:"sequence labelling" OR all:"sequence labeling" OR all:"information extraction" OR all:"text classification" OR all:"sentiment analysis" OR all:"machine translation" OR all:"question answering" OR all:"language generation" OR all:"language application development")
github · term 1 AI "NLP engineering" in:name,description,readme fork:false archived:false
github · term 2 AI "natural language processing" in:name,description,readme fork:false archived:false
github · term 3 AI "language model fine-tuning" in:name,description,readme fork:false archived:false
github · term 4 AI "text processing pipeline" in:name,description,readme fork:false archived:false
github · term 5 AI "named entity recognition" in:name,description,readme fork:false archived:false
github · term 6 AI "sequence labelling" in:name,description,readme fork:false archived:false
github · term 7 AI "sequence labeling" in:name,description,readme fork:false archived:false
github · term 8 AI "information extraction" in:name,description,readme fork:false archived:false
github · term 9 AI "text classification" in:name,description,readme fork:false archived:false
github · term 10 AI "sentiment analysis" in:name,description,readme fork:false archived:false
github · term 11 AI "machine translation" in:name,description,readme fork:false archived:false
github · term 12 AI "question answering" in:name,description,readme fork:false archived:false
github · term 13 AI "language generation" in:name,description,readme fork:false archived:false
github · term 14 AI "language application development" in:name,description,readme fork:false archived:false

Profile 47e344d4b2e76652

Alignment descriptor draft

Outcomes
  • Can build an NLP application: preprocessing, a model, evaluation.
  • Can fine-tune or adapt a language model for a task such as classification or extraction.
  • Can choose techniques and models for a language task.
Develops it

Hands-on material on building NLP systems — tokenisation, embeddings, models, fine-tuning, evaluation — with code the learner runs and modifies.

Only mentions it

A chatbot built by calling an API without any language processing of its own.

Alignment terms
named entity recognitiontext classificationsentiment analysistokenizerhugging face transformersquestion answeringtext summarizationtext summarisation

Read in a resource's text beside the domain group. They are never compiled into a search.

Neighbours

Descriptor 2e4ea97b60b6

How a vocabulary becomes a search

Every candidate must match both concept groups in its title, description or keywords before any content is downloaded. Precision warnings are recorded for audit; they never silently cancel positive evidence.

  1. Official name and description
  2. AI/ML terms and domain terms
  3. Zenodo, arXiv and GitHub syntax
  4. Metadata relevance gate
Mandatory AI/ML group
artificial intelligencemachine learninggenerative AIdeep learningreinforcement learninglarge language modelAI

GitHub's repository search takes one phrase at a time. Measured against the live endpoint, a parenthesised OR group returns nothing at all where each term alone returns thousands, and the 256-character limit rejects a long group outright — so that lane issues one query per term and stops as soon as the competency is satisfied.

coverage-vocabulary-1.3.0+sha256:08ad2cd19868 · catalogue sha256:04970bfc77255b1f

What a descriptor is

A descriptor is how the alignment reads a competency: what a learner who has it can do, what a resource has to do to develop it, what only mentions it, the phrases its subject is written in, its false friends, and how to tell it from the competencies that share its words. The definition above it stays the authority.

Every descriptor is a draft until a partner approves it; 0 of 104 are approved. Read the alignment rubric →

competency-descriptors-1.0.0+sha256:3cc741a61ced