I've problems integrating Bert Embedding Layer in a BiLSTM model for text classification task. My dataset is in the form where each row has 2 columns: text and
toybox
shibboleth-sp
game-maker-language
eclipse-classpath
elgamal
static-html
precompile
alexa-intent
emqx
missing-symbols
install-requires
stochastic
ohlcv
rockset
apim
emscripten
checkpoint
node-postgres
aws-sdk-java
likely-unlikely
shoutem
google-admin-sdk
ondestroy
devspace
twilio-programmable-voice
telerik-reporting
context-bound
appium-ios
gnutls
angular-strap