Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310825265> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4310825265 abstract "Pre-trained language models are trained on large-scale unsupervised data, and they can fine-turn the model only on small-scale labeled datasets, and achieve good results. Multilingual pre-trained language models can be trained on multiple languages, and the model can understand multiple languages at the same time. At present, the search on pre-trained models mainly focuses on rich resources, while there is relatively little research on low-resource languages such as minority languages, and the public multilingual pre-trained language model can not work well for minority languages. Therefore, this paper constructs a multilingual pre-trained model named MiLMo that performs better on minority language tasks, including Mongolian, Tibetan, Uyghur, Kazakh and Korean. To solve the problem of scarcity of datasets on minority languages and verify the effectiveness of the MiLMo model, this paper constructs a minority multilingual text classification dataset named MiTC, and trains a word2vec model for each language. By comparing the word2vec model and the pre-trained model in the text classification task, this paper provides an optimal scheme for the downstream task research of minority languages. The final experimental results show that the performance of the pre-trained model is better than that of the word2vec model, and it has achieved the best results in minority multilingual text classification. The multilingual pre-trained model MiLMo, multilingual word2vec model and multilingual text classification dataset MiTC are published on http://milmo.cmli-nlp.com/." @default.
- W4310825265 created "2022-12-18" @default.
- W4310825265 creator A5009916557 @default.
- W4310825265 creator A5010182723 @default.
- W4310825265 creator A5022231767 @default.
- W4310825265 creator A5022478702 @default.
- W4310825265 creator A5036120236 @default.
- W4310825265 creator A5053129731 @default.
- W4310825265 date "2022-12-04" @default.
- W4310825265 modified "2023-09-26" @default.
- W4310825265 title "MiLMo:Minority Multilingual Pre-trained Language Model" @default.
- W4310825265 doi "https://doi.org/10.48550/arxiv.2212.01779" @default.
- W4310825265 hasPublicationYear "2022" @default.
- W4310825265 type Work @default.
- W4310825265 citedByCount "0" @default.
- W4310825265 crossrefType "posted-content" @default.
- W4310825265 hasAuthorship W4310825265A5009916557 @default.
- W4310825265 hasAuthorship W4310825265A5010182723 @default.
- W4310825265 hasAuthorship W4310825265A5022231767 @default.
- W4310825265 hasAuthorship W4310825265A5022478702 @default.
- W4310825265 hasAuthorship W4310825265A5036120236 @default.
- W4310825265 hasAuthorship W4310825265A5053129731 @default.
- W4310825265 hasBestOaLocation W43108252651 @default.
- W4310825265 hasConcept C137293760 @default.
- W4310825265 hasConcept C138885662 @default.
- W4310825265 hasConcept C154945302 @default.
- W4310825265 hasConcept C162324750 @default.
- W4310825265 hasConcept C187736073 @default.
- W4310825265 hasConcept C204321447 @default.
- W4310825265 hasConcept C2776461190 @default.
- W4310825265 hasConcept C2780035574 @default.
- W4310825265 hasConcept C2780451532 @default.
- W4310825265 hasConcept C41008148 @default.
- W4310825265 hasConcept C41608201 @default.
- W4310825265 hasConcept C41895202 @default.
- W4310825265 hasConceptScore W4310825265C137293760 @default.
- W4310825265 hasConceptScore W4310825265C138885662 @default.
- W4310825265 hasConceptScore W4310825265C154945302 @default.
- W4310825265 hasConceptScore W4310825265C162324750 @default.
- W4310825265 hasConceptScore W4310825265C187736073 @default.
- W4310825265 hasConceptScore W4310825265C204321447 @default.
- W4310825265 hasConceptScore W4310825265C2776461190 @default.
- W4310825265 hasConceptScore W4310825265C2780035574 @default.
- W4310825265 hasConceptScore W4310825265C2780451532 @default.
- W4310825265 hasConceptScore W4310825265C41008148 @default.
- W4310825265 hasConceptScore W4310825265C41608201 @default.
- W4310825265 hasConceptScore W4310825265C41895202 @default.
- W4310825265 hasLocation W43108252651 @default.
- W4310825265 hasOpenAccess W4310825265 @default.
- W4310825265 hasPrimaryLocation W43108252651 @default.
- W4310825265 hasRelatedWork W142374489 @default.
- W4310825265 hasRelatedWork W1563618553 @default.
- W4310825265 hasRelatedWork W2081647779 @default.
- W4310825265 hasRelatedWork W2148757832 @default.
- W4310825265 hasRelatedWork W2359001871 @default.
- W4310825265 hasRelatedWork W2746217931 @default.
- W4310825265 hasRelatedWork W2810280135 @default.
- W4310825265 hasRelatedWork W3107474891 @default.
- W4310825265 hasRelatedWork W3185852197 @default.
- W4310825265 hasRelatedWork W4205820553 @default.
- W4310825265 isParatext "false" @default.
- W4310825265 isRetracted "false" @default.
- W4310825265 workType "article" @default.