← Back to Urdu on IDLI

Stanza · Aug 5, 15:15 UTC

Urdu urd

View upstream

Figures

Pipeline processors
5
of 9 possible
Tokenization stages
1
of 2 (tokenize, mwt)
Analysis stages
4
pos/lemma/depparse/ner/sentiment/constituency/coref

Detail

Processors present
depparse, lemma, ner, pos, tokenize
Stanza language code
ur
Stanza language name
Urdu

Notes from Stanza

  • Languages with only character-language-model embeddings (no tokenizer or tagger of their own) are excluded -- they aren't a runnable pipeline.
  • Processor count is a coverage signal, not an accuracy signal: a 9-processor pipeline can still perform unevenly across individual processors.

Source

Compare with other languages in Stanza

Source snapshot: stanza_2026-08-05_1515.json · harvested Aug 5, 15:15 UTC

Who is working on Urdu

Opportunities, events, and experts across the digital language inclusion ecosystem, filtered to Urdu.