com.johnsnowlabs.nlp.embeddings
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI
takes a document and annotations and produces new annotations of this annotator's annotation type
takes a document and annotations and produces new annotations of this annotator's annotation type
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
any number of annotations processed for every input annotation. Not necessary one to one relationship
Size of every batch (Default depends on model).
Size of every batch (Default depends on model).
Whether to ignore case in index lookups (Default depends on model)
Whether to ignore case in index lookups (Default depends on model)
ConfigProto from tensorflow, serialized into byte array.
ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()
requirement for annotators copies
requirement for annotators copies
Number of embedding dimensions (Default depends on model)
Number of embedding dimensions (Default depends on model)
Override for additional custom schema checks
Override for additional custom schema checks
Size of every batch.
Size of every batch.
input annotations columns currently used
Gets annotation column name going to generate
Gets annotation column name going to generate
Input Annotator Types: DOCUMENT, TOKEN
Input Annotator Types: DOCUMENT, TOKEN
columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified
columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified
Max sentence length to process (Default: 128)
Output Annotator Types: WORD_EMBEDDINGS
Output Annotator Types: WORD_EMBEDDINGS
Size of every batch.
Size of every batch.
Whether to lowercase tokens or not
Whether to lowercase tokens or not
Set Embeddings dimensions for the XLM-RoBERTa model.
Set Embeddings dimensions for the XLM-RoBERTa model. Only possible to set this when the first time is saved dimension is not changeable, it comes from XLM-RoBERTa config file.
Overrides required annotators column if different than default
Overrides required annotators column if different than default
Overrides annotation column name when transforming
Overrides annotation column name when transforming
It contains TF model signatures for the laded saved model
Unique identifier for storage (Default: this.uid)
Unique identifier for storage (Default: this.uid)
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
Dataset[Row]
requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()
takes a Dataset and checks to see if all the required annotation types are present.
takes a Dataset and checks to see if all the required annotation types are present.
to be validated
True if all the required types are present, else false
A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.
Required input and expected output annotator types
Sentence-level embeddings using XLM-RoBERTa. 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.
Pretrained models can be loaded with
pretrainedof the companion object:The default model is
"sent_xlm_roberta_base", default language is"xx"(meaning multi-lingual), if no values are provided. For available pretrained models please see the Models Hub.Models from the HuggingFace 🤗 Transformers library are also compatible with Spark NLP 🚀. The Spark NLP Workshop example shows how to import them https://github.com/JohnSnowLabs/spark-nlp/discussions/5669. and the XlmRoBertaSentenceEmbeddingsTestSpec.
Paper Abstract:
This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages, using more than two terabytes of filtered CommonCrawl data. Our model, dubbed XLM-R, significantly outperforms multilingual BERT (mBERT) on a variety of cross-lingual benchmarks, including +13.8% average accuracy on XNLI, +12.3% average F1 score on MLQA, and +2.1% average F1 score on NER. XLM-R performs particularly well on low-resource languages, improving 11.8% in XNLI accuracy for Swahili and 9.2% for Urdu over the previous XLM model. We also present a detailed empirical evaluation of the key factors that are required to achieve these gains, including the trade-offs between (1) positive transfer and capacity dilution and (2) the performance of high and low resource languages at scale. Finally, we show, for the first time, the possibility of multilingual modeling without sacrificing per-language performance; XLM-Ris very competitive with strong monolingual models on the GLUE and XNLI benchmarks. We will make XLM-R code, data, and models publicly available.
Tips:
Example
Annotators Main Page for a list of transformer based embeddings