# 82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models

arXiv: https://arxiv.org/abs/1809.02237 · HTML: https://mlsanity.com/paper/1809.02237/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2018.

## Built on by (most cited first, 11 of 11)

- [PyThaiNLP: Thai Natural Language Processing in Python](https://mlsanity.com/paper/2312.04649/) (2023)
- [A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021](https://mlsanity.com/paper/2106.04216/) (2021)
- [On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions](https://mlsanity.com/paper/2103.01273/) (2021)
- [How Universal is Genre in Universal Dependencies?](https://mlsanity.com/paper/2112.04971/) (2021)
- [Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing](https://mlsanity.com/paper/2201.11374/) (2022)
- [Data-driven Parsing Evaluation for Child-Parent Interactions](https://mlsanity.com/paper/2209.13778/) (2022)
- [Syntactic Nuclei in Dependency Parsing -- A Multilingual Exploration](https://mlsanity.com/paper/2101.11959/) (2021)
- [Parsing with Pretrained Language Models, Multiple Datasets, and Dataset Embeddings](https://mlsanity.com/paper/2112.03625/) (2021)
- [Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?](https://mlsanity.com/paper/2410.10576/) (2024)
- [How to Encode Domain Information in Relation Classification](https://mlsanity.com/paper/2404.13760/) (2024)
- [Building Tamil Treebanks](https://mlsanity.com/paper/2409.14657/) (2024)

## Abstract (arXiv)

We present the Uppsala system for the CoNLL 2018 Shared Task on universal dependency parsing. Our system is a pipeline consisting of three components: the first performs joint word and sentence segmentation; the second predicts part-of- speech tags and morphological features; the third predicts dependency trees from words and tags. Instead of training a single parsing model for each treebank, we trained models with multiple treebanks for one language or closely related languages, greatly reducing the number of models. On the official test run, we ranked 7th of 27 teams for the LAS and MLAS metrics. Our system obtained the best scores overall for word segmentation, universal POS tagging, and morphological features.