Sequence-Semantic-Embedding
Sequence-Semantic-Embedding copied to clipboard
eBay
Tools and recipes to train deep learning models and build services for NLP tasks such as text classification, semantic search ranking and recall fetching, cross-lingual information retrieval, and ques...
ub16hp@UB16HP:~/ub16_prj/Sequence-Semantic-Embedding$ make train-crosslingual python sse_train.py --task_type=crosslingual --data_dir=rawdata-crosslingual --model_dir=models-crosslingual --device=0 --learning_rate=0.9 --embedding_size=40 --encoding_size=50 --max_seq_length=50 --batch_size=32 --max_epoc=1000 --steps_per_checkpoint=200 --network_mode=shared-encoder Traceback (most recent call last): File "sse_train.py", line 44, in import tensorflow as...
Some commands seem to depreciated with latest versions, can you add version numbers to requirements
Why are the labels in qa task selected randomly? ? Is there some theory supporting this?
