XLM-RoBERTa XTREME Base (xlm_roberta_xtreme_base)

Description

This model is a fine-tuned XLM-Roberta base model over the 40 languages provided by XTREME from Wikiann. We used Masked language modeling (MLM) by randomly masking 15% of the dataset ([MASK]).

XLM-RoBERTa is a scaled cross-lingual sentence encoder. It is trained on 2.5T of data across 100 languages data filtered from Common Crawl. XLM-R achieves state-of-the-arts results on multiple cross-lingual benchmarks.

The XLM-RoBERTa model was proposed in Unsupervised Cross-lingual Representation Learning at Scale by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov.

It is based on Facebook’s RoBERTa model released in 2019. It is a large multi-lingual language model, trained on 2.5TB of filtered CommonCrawl data.

Download

How to use

embeddings = XlmRoBertaEmbeddings.pretrained("xlm_roberta_xtreme_base", "xx") \
      .setInputCols("sentence", "token") \
      .setOutputCol("embeddings")
val embeddings = XlmRoBertaEmbeddings.pretrained("xlm_roberta_xtreme_base", "xx")
      .setInputCols("sentence", "token")
      .setOutputCol("embeddings")

Model Information

Model Name: xlm_roberta_xtreme_base
Compatibility: Spark NLP 3.1.3+
License: Open Source
Edition: Official
Input Labels: [token, sentence]
Output Labels: [embeddings]
Language: xx
Case sensitive: true
Max sentense length: 128

Data Source