API for BERT-based Conversational Language Understanding.
The API expects a Bert based TFLite model with metadata populated. The metadata should contain the following information:
class | BertCluAnnotator.BertCluAnnotatorOptions | Options for setting up a BertCluAnnotator . |
CluResponse | |
static BertCluAnnotator |
createFromBufferAndOptions(ByteBuffer modelBuffer, BertCluAnnotator.BertCluAnnotatorOptions options)
Creates a
BertCluAnnotator instance with a model buffer and BertCluAnnotator.BertCluAnnotatorOptions . |
static BertCluAnnotator |
createFromFile(Context context, String modelPath)
Creates a
BertCluAnnotator instance from a filepath. |
Annotates the input utterances.
cluRequest | input dialogue encoded in a CluRequest |
---|
CluResponse
Creates a BertCluAnnotator
instance with a model buffer and BertCluAnnotator.BertCluAnnotatorOptions
.
modelBuffer | a direct ByteBuffer or a MappedByteBuffer of the annotator
model |
---|---|
options |
IllegalArgumentException | if the model buffer is not a direct ByteBuffer or a
MappedByteBuffer |
---|---|
IllegalStateException | if there is an internal error |
RuntimeException | if there is an otherwise unspecified error |
Creates a BertCluAnnotator
instance from a filepath.
context | |
---|---|
modelPath | path of the annotator model |
IOException | if an I/O error occurs when loading the tflite model |
---|---|
IllegalArgumentException | if an argument is invalid |
IllegalStateException | if there is an internal error |
RuntimeException | if there is an otherwise unspecified error |