# On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions

arXiv: https://arxiv.org/abs/2103.01273 · HTML: https://mlsanity.com/paper/2103.01273/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 11 of 11)

- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection](https://mlsanity.com/paper/1910.11493/) (2019)
- [UniMorph 2.0: Universal Morphology](https://mlsanity.com/paper/1810.11101/) (2018)
- [Many Languages, One Parser](https://mlsanity.com/paper/1602.01595/) (2016)
- [82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models](https://mlsanity.com/paper/1809.02237/) (2018)
- [Parser Training with Heterogeneous Treebanks](https://mlsanity.com/paper/1805.05089/) (2018)
- [Joining Hands: Exploiting Monolingual Treebanks for Parsing of Code-mixing Data](https://mlsanity.com/paper/1703.10772/) (2017)
- [Cross-lingual Parsing with Polyglot Training and Multi-treebank Learning: A Faroese Case Study](https://mlsanity.com/paper/1910.07938/) (2019)
- [Treebank Embedding Vectors for Out-of-domain Dependency Parsing](https://mlsanity.com/paper/2005.00800/) (2020)

## Built on by (most cited first, 4 of 4)

- [Can Humans Identify Domains?](https://mlsanity.com/paper/2404.01785/) (2024)
- [Federated Learning for Heterogeneous Electronic Health Record Systems with Cost Effective Participant Selection](https://mlsanity.com/paper/2404.13318/) (2024)
- [ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language](https://mlsanity.com/paper/2203.07742/) (2022)
- [How to Encode Domain Information in Relation Classification](https://mlsanity.com/paper/2404.13760/) (2024)

## Abstract (arXiv)

Recent complementary strands of research have shown that leveraging information on the data source through encoding their properties into embeddings can lead to performance increase when training a single model on heterogeneous data sources. However, it remains unclear in which situations these dataset embeddings are most effective, because they are used in a large variety of settings, languages and tasks. Furthermore, it is usually assumed that gold information on the data source is available, and that the test data is from a distribution seen during training. In this work, we compare the effect of dataset embeddings in mono-lingual settings, multi-lingual settings, and with predicted data source label in a zero-shot setting. We evaluate on three morphosyntactic tasks: morphological tagging, lemmatization, and dependency parsing, and use 104 datasets, 66 languages, and two different dataset grouping strategies. Performance increases are highest when the datasets are of the same language, and we know from which distribution the test-instance is drawn. In contrast, for setups where the data is from an unseen distribution, performance increase vanishes.