# Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity

arXiv: https://arxiv.org/abs/2009.03116 · HTML: https://mlsanity.com/paper/2009.03116/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [ScandEval: A Benchmark for Scandinavian Natural Language Processing](https://mlsanity.com/paper/2304.00906/) (2023)
- [Cross-lingual Transfer of Monolingual Models](https://mlsanity.com/paper/2109.07348/) (2021)
- [Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish](https://mlsanity.com/paper/2309.06698/) (2023)

## Abstract (arXiv)

This paper presents the first Swedish evaluation benchmark for textual semantic similarity. The benchmark is compiled by simply running the English STS-B dataset through the Google machine translation API. This paper discusses potential problems with using such a simple approach to compile a Swedish evaluation benchmark, including translation errors, vocabulary variation, and productive compounding. Despite some obvious problems with the resulting dataset, we use the benchmark to compare the majority of the currently existing Swedish text representations, demonstrating that native models outperform multilingual ones, and that simple bag of words performs remarkably well.