[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/ud-2016-straka-udpipe-trainable-pipeline-processing-conll/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing

# UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing

**Authors:** [Milan Straka](https://md.mova.elamur.ai/free/en/docs/papers/authors/milan-straka/), [Jan Hajič](https://md.mova.elamur.ai/free/en/docs/papers/authors/jan-hajic/), [Jana Straková](https://md.mova.elamur.ai/free/en/docs/papers/authors/jana-strakova/) · **Year:** 2016 · **Venue:** Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16) **Link:** [aclanthology.org/L16-1680](https://aclanthology.org/L16-1680/) · **Licence:** [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) (LREC proceedings) — summary only

[**350** citations](https://openalex.org/works?filter=cites:W2574640638) openalex-snapshot · 2026-10-14[**128** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/ud-2016-straka-udpipe-trainable-pipeline-processing-conll/) of the 140673 papers whose bibliographies we read[Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)](https://aclanthology.org/volumes/L16-1/)[licence](https://creativecommons.org/licenses/by-nc/4.0/)

- [Publisher's page](https://aclanthology.org/L16-1680/)
- [PDF](https://aclanthology.org/L16-1680.pdf)
- [DOI 10.63317/2q6bwb9anobz](https://doi.org/10.63317/2q6bwb9anobz)
- [OpenAlex](https://openalex.org/W2574640638)

**Authors (3)**

1. [Milan Straka](https://openalex.org/A5060081515) [ORCID](https://orcid.org/0000-0003-3295-5576) · h 22 · 3074 citations · 127 works
2. [Jan Hajič](https://openalex.org/A5102738283) [ORCID](https://orcid.org/0000-0002-3503-7730) · h 39 · 8442 citations · 278 works
3. [Jana Straková](https://openalex.org/A5047678040) [ORCID](https://orcid.org/0000-0003-0075-2408) · h 12 · 1660 citations · 56 works

Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart.

## What it is about

UDPipe is one binary with one model per language that turns raw text into CoNLL-U: tokenisation, morphological analysis, tagging, lemmatisation and dependency parsing. The tokeniser is a GRU over characters that predicts sentence and token boundaries together. When a treebank lacks SpaceAfter=No, the paper fills it in by comparing counts of word pairs with and without a space in a raw corpus. Tagging uses a suffix-based guesser of analyses with an averaged perceptron, and parsing uses the Parsito transition parser with a small neural classifier, a search-based oracle and a beam of 5. The authors released models for 32 of the 37 UD 1.2 treebanks, and the whole pipeline needs no dictionaries or feature engineering. The paper presents the tool and its trainability, and gives tokenisation results against baselines (Table 1) and parsing results against Ammar et al. (2016).

## Ideas

- I1. en/src/tok.rs: for treebanks whose converter cannot align SpaceAfter, fill the missing SpaceAfter=No by the paper's count rule over a raw corpus, and measure token F1 against the aligned original on EWT with the spacing removed.
- I2. en/src/morph.rs: test a suffix guesser for words missing from the dictionary (analyses per fixed-length suffix, with the shortest lemma rule) and measure UPOS accuracy on out-of-dictionary tokens of EWT dev through `en tag-eval`.
- I3. en beam-curve: check on EWT dev that the beam of 8 is on the flat part of the curve (the 2017 UDPipe paper finds that a large fixed beam beats per-treebank beam tuning), and drop the beam to save time if it is.

## For Mova

The ideas touch the tokeniser `en/src/tok.rs`, the lexicon and guesser in `en/src/morph.rs` and `en/src/ptag.rs`, and the beam in `en/src/parse.rs`. The chapters are `languages/en/07-punctuation-capitals-numbers` and `languages/en/10-word-classes`. Measure first I3, since `en beam-curve` already exists and the answer changes only the speed budget.

Topics: [Universal Dependencies](https://md.mova.elamur.ai/free/en/docs/papers/topics/universal-dependencies/) · [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/) · [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/)

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.63317/2q6bwb9anobz](https://doi.org/10.63317/2q6bwb9anobz)

```
@inproceedings{straka2016udpipe,
  title = {{UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing}},
  author = {Straka, Milan and Hajič, Jan and Straková, Jana},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  doi = {10.63317/2q6bwb9anobz},
  url = {https://doi.org/10.63317/2q6bwb9anobz}
}
```

- [← previous Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks](https://md.mova.elamur.ai/free/en/docs/papers/ud-2016-schuster-enhanced-english-universal-dependencies-improved/)
- [next → The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages](https://md.mova.elamur.ai/free/en/docs/papers/ud-2016-wang-galactic-dependencies-treebanks-getting-more/)
- [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/)