If i use the Graph2Seq mode to NLG,what's the data form should i organize?Or 'g_ids','g_features' mean what?

IBM / Graph2Seq

Graph2Seq is a simple code for building a graph-encoder and sequence-decoder for NLP and other AI/ML/DL tasks.

Apache License 2.0

236 stars 61 forks source link

If i use the Graph2Seq mode to NLG,what's the data form should i organize?Or 'g_ids','g_features' mean what? #1

Open hengqiali opened 5 years ago

hengqiali commented 5 years ago

help me

syxu828 commented 5 years ago

help me

g_ids means the graph id and g_features means the string feature of a node. In the case of NLG, the graph can be generated from SQL query using the method mentioned in the paper.

syxu828 commented 5 years ago

help me

If you have any implementation problem, you can email me syxu828@gmail.com.

teddylfwu commented 3 years ago

Dear All,

Please see our newly released graph4nlp library: https://github.com/graph4ai/graph4nlp, which have implemented many GNN methods like Graph2Seq and Graph2Tree models.