Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity
This provides an initial evaluation benchmark for Swedish semantic similarity tasks, though it is incremental due to its simple translation-based construction.
The authors created the first Swedish semantic similarity benchmark by machine-translating the English STS-B dataset, then used it to evaluate Swedish text representations, finding that native models outperform multilingual ones and simple bag-of-words approaches work surprisingly well.
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.