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.
Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity
A Swedish textual semantic similarity benchmark compiled via English translation reveals that native models outperform multilingual models and simple methods like Bag of Words.
- Year
- 2020
- Venue
- arXiv 2020
- Authors
- 2
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2009.03116v2ARXIV-DEFAULT
- TL;DR
- Semantic Scholar