# Many Languages, One Parser

arXiv: https://arxiv.org/abs/1602.01595 · HTML: https://mlsanity.com/paper/1602.01595/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2016.

## Built on by (most cited first, 26 of 26)

- [Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations](https://mlsanity.com/paper/2303.18027/) (2023)
- [Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning](https://mlsanity.com/paper/2204.11117/) (2022)
- [Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer](https://mlsanity.com/paper/2105.05975/) (2021)
- [PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs](https://mlsanity.com/paper/2303.08954/) (2023)
- [Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing](https://mlsanity.com/paper/2104.04736/) (2021)
- [Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?](https://mlsanity.com/paper/2212.10879/) (2022)
- [Does Typological Blinding Impede Cross-Lingual Sharing?](https://mlsanity.com/paper/2101.11888/) (2021)
- [A Dataset and Baselines for Multilingual Reply Suggestion](https://mlsanity.com/paper/2106.02017/) (2021)
- [Using Linguistic Typology to Enrich Multilingual Lexicons: the Case of Lexical Gaps in Kinship](https://mlsanity.com/paper/2204.05049/) (2022)
- [Language Embeddings Sometimes Contain Typological Generalizations](https://mlsanity.com/paper/2301.08115/) (2023)
- [Language Embeddings for Typology and Cross-lingual Transfer Learning](https://mlsanity.com/paper/2106.02082/) (2021)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization](https://mlsanity.com/paper/2310.12794/) (2023)
- [Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing](https://mlsanity.com/paper/2110.08538/) (2021)
- [On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?](https://mlsanity.com/paper/2406.14267/) (2024)
- [On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions](https://mlsanity.com/paper/2103.01273/) (2021)
- [On the Relation between Syntactic Divergence and Zero-Shot Performance](https://mlsanity.com/paper/2110.04644/) (2021)
- [Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering](https://mlsanity.com/paper/2310.13583/) (2023)
- [Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities](https://mlsanity.com/paper/2505.15722/) (2025)
- [Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach](https://mlsanity.com/paper/2308.04645/) (2023)
- [LangSAMP: Language-Script Aware Multilingual Pretraining](https://mlsanity.com/paper/2409.18199/) (2024)
- [Parsing with Pretrained Language Models, Multiple Datasets, and Dataset Embeddings](https://mlsanity.com/paper/2112.03625/) (2021)
- [Cross-lingual Inflection as a Data Augmentation Method for Parsing](https://mlsanity.com/paper/2205.09350/) (2022)
- [Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization](https://mlsanity.com/paper/2210.09428/) (2022)
- [How to Encode Domain Information in Relation Classification](https://mlsanity.com/paper/2404.13760/) (2024)
- [Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch](https://mlsanity.com/paper/2410.18430/) (2024)

## Abstract (arXiv)

We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii) language-specific features (fine-grained POS tags). This input representation enables the parser not only to parse effectively in multiple languages, but also to generalize across languages based on linguistic universals and typological similarities, making it more effective to learn from limited annotations. Our parser's performance compares favorably to strong baselines in a range of data scenarios, including when the target language has a large treebank, a small treebank, or no treebank for training.