embeddings

Type Members

1. class AlbertEmbeddings extends AnnotatorModel[AlbertEmbeddings] with WriteTensorflowModel with WriteSentencePieceModel with HasEmbeddingsProperties with HasStorageRef with HasCaseSensitiveProperties

   

   ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS - Google Research, Toyota Technological Institute at Chicago This these embeddings represent the outputs generated by the Albert model.

   ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS - Google Research, Toyota Technological Institute at Chicago This these embeddings represent the outputs generated by the Albert model. All offical Albert releases by google in TF-HUB are supported with this Albert Wrapper:

   TF-HUB Models : albert_base = https://tfhub.dev/google/albert_base/3 | 768-embed-dim, 12-layer, 12-heads, 12M parameters albert_large = https://tfhub.dev/google/albert_large/3 | 1024-embed-dim, 24-layer, 16-heads, 18M parameters albert_xlarge = https://tfhub.dev/google/albert_xlarge/3 | 2048-embed-dim, 24-layer, 32-heads, 60M parameters albert_xxlarge = https://tfhub.dev/google/albert_xxlarge/3 | 4096-embed-dim, 12-layer, 64-heads, 235M parameters

   This model requires input tokenization with SentencePiece model, which is provided by Spark-NLP (See tokenizers package)

   For additional information see : https://arxiv.org/pdf/1909.11942.pdf https://github.com/google-research/ALBERT https://tfhub.dev/s?q=albert

   Tips:

   ALBERT uses repeating layers which results in a small memory footprint, however the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.

2. class BertEmbeddings extends AnnotatorModel[BertEmbeddings] with WriteTensorflowModel with HasEmbeddingsProperties with HasStorageRef with HasCaseSensitiveProperties

   

3. class ChunkEmbeddings extends AnnotatorModel[ChunkEmbeddings]

   

4. class ElmoEmbeddings extends AnnotatorModel[ElmoEmbeddings] with WriteTensorflowModel with HasEmbeddingsProperties with HasStorageRef with HasCaseSensitiveProperties

   

   Embeddings from a language model trained on the 1 Billion Word Benchmark.

   Embeddings from a language model trained on the 1 Billion Word Benchmark.

   Note that this is a very computationally expensive module compared to word embedding modules that only perform embedding lookups. The use of an accelerator is recommended.

5. trait EmbeddingsCoverage extends AnyRef

   

6. trait HasEmbeddingsProperties extends Params

   

7. trait ReadAlbertTensorflowModel extends ReadTensorflowModel with ReadSentencePieceModel

   

8. trait ReadBertTensorflowModel extends ReadTensorflowModel

   

9. trait ReadElmoTensorflowModel extends ReadTensorflowModel

   

10. trait ReadUSETensorflowModel extends ReadTensorflowModel

    

11. trait ReadXlnetTensorflowModel extends ReadTensorflowModel with ReadSentencePieceModel

    

12. trait ReadablePretrainedAlbertModel extends ParamsAndFeaturesReadable[AlbertEmbeddings] with HasPretrained[AlbertEmbeddings]

    

13. trait ReadablePretrainedBertModel extends ParamsAndFeaturesReadable[BertEmbeddings] with HasPretrained[BertEmbeddings]

    

14. trait ReadablePretrainedElmoModel extends ParamsAndFeaturesReadable[ElmoEmbeddings] with HasPretrained[ElmoEmbeddings]

    

15. trait ReadablePretrainedUSEModel extends ParamsAndFeaturesReadable[UniversalSentenceEncoder] with HasPretrained[UniversalSentenceEncoder]

    

16. trait ReadablePretrainedWordEmbeddings extends StorageReadable[WordEmbeddingsModel] with HasPretrained[WordEmbeddingsModel]

    

17. trait ReadablePretrainedXlnetModel extends ParamsAndFeaturesReadable[XlnetEmbeddings] with HasPretrained[XlnetEmbeddings]

    

18. trait ReadsFromBytes extends AnyRef

    

19. class SentenceEmbeddings extends AnnotatorModel[SentenceEmbeddings] with HasEmbeddingsProperties with HasStorageRef

    

20. class UniversalSentenceEncoder extends AnnotatorModel[UniversalSentenceEncoder] with HasEmbeddingsProperties with HasStorageRef with WriteTensorflowModel

    

21. class WordEmbeddings extends AnnotatorApproach[WordEmbeddingsModel] with HasStorage with HasEmbeddingsProperties

    

22. class WordEmbeddingsModel extends AnnotatorModel[WordEmbeddingsModel] with HasEmbeddingsProperties with HasStorageModel with ParamsAndFeaturesWritable

    

23. class WordEmbeddingsReader extends StorageReader[Array[Float]] with ReadsFromBytes

    

24. class WordEmbeddingsWriter extends StorageBatchWriter[Array[Float]] with ReadsFromBytes

    

25. class XlnetEmbeddings extends AnnotatorModel[XlnetEmbeddings] with WriteTensorflowModel with WriteSentencePieceModel with HasEmbeddingsProperties with HasStorageRef with HasCaseSensitiveProperties

    

    XlnetEmbeddings (XLNet): Generalized Autoregressive Pretraining for Language Understanding

    XlnetEmbeddings (XLNet): Generalized Autoregressive Pretraining for Language Understanding

    Note that this is a very computationally expensive module compared to word embedding modules that only perform embedding lookups. The use of an accelerator is recommended.