paper-with-me

홈 › Papers

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

2020-09-07 · Tim Isbister, Magnus Sahlgren

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.

📄 PDF Abstract BibTeX arXiv:2009.03116

Code (1)

timpal0l/sts-benchmark-swedish 공식 구현

Tasks

Machine TranslationSemantic SimilaritySemantic Textual SimilaritySTSSTS-BTranslation

Similar Papers 제목 키워드 기반

Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets

2023-01-28 · Tosin Adewumi, Isabella Södergren, Lama Alkhaled, Sana Sabah Sabry 외

We investigate five English NLP benchmark datasets (on the superGLUE leaderboard) and two Swedish datasets for bias, along multiple axes. The datasets are the following: Boolean Question (Boolq), CommitmentBank (CB), Win…

Bias DetectionDiagnosticNatural Language InferenceRTE

Preferences for Idiomatic Language are Acquired Slowly -- and Forgotten Quickly: A Case Study on Swedish

2026-02-03 · Jenny Kunz arxiv

In this study, we investigate how language models develop preferences for \textit{idiomatic} as compared to \textit{linguistically acceptable} Swedish, both during pretraining and when adapting a model from English to Sw…

Linguistic Acceptability

A Parallel WordNet for English, Swedish and Bulgarian

2020-05-01 · LREC 2020 5 · Krasimir Angelov

We present the parallel creation of a WordNet resource for Swedish and Bulgarian which is tightly aligned with the Princeton WordNet. The alignment is not only on the synset level, but also on word level, by matching wor…

ArticlesMachine TranslationText GenerationTranslation

The FISKM\"O Project: Resources and Tools for Finnish-Swedish Machine Translation and Cross-Linguistic Research

2020-05-01 · LREC 2020 5 · J{\"o}rg Tiedemann, Tommi Nieminen, Mikko Aulamo, Jenna Kanerva 외

This paper presents FISKM{\"O}, a project that focuses on the development of resources and tools for cross-linguistic research and machine translation between Finnish and Swedish. The goal of the project is the compilati…

Machine TranslationTranslation

Lessons Learned from GPT-SW3: Building the First Large-Scale Generative Language Model for Swedish

2022-06-01 · LREC 2022 6 · Ariel Ekgren, Amaru Cuba Gyllensten, Evangelia Gogoulou, Alice Heiman 외

We present GTP-SW3, a 3.5 billion parameter autoregressive language model, trained on a newly created 100 GB Swedish corpus. This paper provides insights with regards to data collection and training, while highlights the…

Language ModelingLanguage ModellingText Generation