Tools and APIs for preparing data for Neural Structured Learning.

In addition to the functions exported here, two of the modules can be invoked from the command-line.

Sample usage for running the graph builder:

python -m [flags] embedding_file.tfr... output_graph.tsv

Sample usage for preparing input for graph-based NSL:

python -m [flags] labeled.tfr unlabeled.tfr graph.tsv output.tfr

For details about these programs' flags, run these commands:

$ python -m --help
$ python -m --help


graph_utils module: Utility functions for manipulating (weighted) graphs.


add_edge(...): Adds an edge to a given graph.

add_undirected_edges(...): Makes all edges of the given graph bi-directional.

build_graph(...): Like, but with individual parameters.

build_graph_from_config(...): Builds a graph based on dense embeddings and persists it in TSV format.

pack_nbrs(...): Prepares input for graph-based Neural Structured Learning and persists it.

read_tsv_graph(...): Reads the file filename containing graph edges in TSV format.

write_tsv_graph(...): Writes the given graph to the file filename in TSV format.