Exploring Swedish & English fastText Embeddings for NER with the Transformer

In this paper, our main contributions are that embeddings from relatively smaller corpora can outperform ones from far larger corpora and we present the new Swedish analogy test set. To achieve a g ...

cs.CL cs.LG Natural Language Processing Techniques Topic Modeling Speech Recognition and Synthesis

Paper

Similar papers

Corpora Compared : The Case of the Swedish Gigaword & Wikipedia CorporaAdewumi, Oluwatosin, Liwicki, Foteini, Liwicki, Marcus2020 · Epubl LTU In Library

Corpora Compared: The Case of the Swedish Gigaword & Wikipedia CorporaTosin Adewumi, Foteini Liwicki, Marcus Liwicki2020 · arXiv (Cornell University) In Library

Playing with Words at the National Library of Sweden -- Making a Swedish BERTMartin Malmsten, Love Börjeson, Chris Haffenden2020 · arXiv.org · 140 citations In Library

Multilingual Culture-Independent Word Analogy DatasetsMatej Ulčar, M. Robnik-Sikonja2019 · International Conference on Language Resources and Evaluation · 17 citations In Library

Evaluation of Word Embedding Models in Latvian NLP Tasks Based on Publicly Available CorporaRolands Laucis, Gints Jēkabsons2021 · Applied Computer Systems · 2 citations In Library

High Quality ELMo Embeddings for Seven Less-Resourced LanguagesMatej Ulvcar, M. Robnik-Sikonja2019 · International Conference on Language Resources and Evaluation · 26 citations In Library

Learning Word Embeddings for Ukrainian: A Comparative Study of FastText HyperparametersNataliia Romanyshyn, Dmytro Chaplynskyi, Kyrylo Zakharov2023 In Library

Corpora Compared : The Case of the Swedish Gigaword a Wikipedia CorporaOluwatosin Adewumi, Foteini Liwicki, Marcus Liwicki2020 · Language and Technology Conference In Library

Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASRBalázs Tarján, György Szaszák, Tibor Fegyó et al.2020 · arXiv (Cornell University) · 4 citations In Library

Part-of-speech tagging of Swedish texts in the neural era.Yvonne Adesam, Aleksandrs Berdičevskis2021 · DSpace repository (University of Tartu) In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal