MV-LSTM

An implementation of "A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations" in Tensorflow

NOTE: Input Data should be transformed into wordID sequence, and each Word embedding is pre-trained.

Requirement

Python 2.7
Tensorflow 1.0
Numpy

sh run.sh

need to add

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
model		model
pytextnet		pytextnet
README.md		README.md
data0_utils.py		data0_utils.py
model.config		model.config
run.sh		run.sh
train_global.py		train_global.py