Skip to main content

Toolbox for constructing NETworks of Transcript Semantics.

Project description

netts - NETworks of Transcript Semantics

GitHub release PyPI pyversions codecov Code style: black Imports: isort

Toolbox for constructing semantic speech networks from speech transcripts.


The algorithms in this toolbox create a semantic speech graph from transcribed speech. Speech transcripts are short paragraphs of largely raw, uncleaned speech-like text. For example:

'I see a man in the dark standing against a light post. It seems to be in the middle of the night; I think because the lightbulb is working. On the picture there seems to be like a park and... Or trees but in those trees there are little balls of light reflections as well. I cannot see the… Anything else because it’s very dark. But the man on the picture seems to wear a hat and, and has a jacket on and he seems to have a hoodie on as well. The picture is very, very mysterious, which I like about it, but for me I would like to understand more concept, context of the picture.' -- Example Transcript

Below is the semantic speech graph constructed from this text.

Semantic speech graph example Figure 1. Semantic Speech Graph. Nodes represents an entity mentioned by the speaker (e.g. I, man, jacket). Edges represent relations between nodes mentioned by the speaker (e.g. see, has on).

Getting started

Read the full documentation here.

Where to get it

You can install the latest release from PyPi

pip install netts

or get the latest development version from GitHub (not stable)

pip install git+

Additional dependencies

Netts requires a few additional dependencies to work which you can download with the netts CLI that was installed by pip

netts install

Basic usage

The quickest way to process a transcript is with the CLI.

netts run transcript.txt outputs

where transcript.txt is a text file containing transcribed speech and outputs is the name of a directory to write the outputs to.


Netts was written by Caroline Nettekoven in collaboration with Sarah Morgan.

Netts was packaged in collaboration with Oscar Giles, Iain Stenson and Helen Duncan.

Citing netts

If you use netts in your work, please cite this paper:

Caroline R. Nettekoven, Kelly Diederen, Oscar Giles, Helen Duncan, Iain Stenson, Julianna Olah, Nigel Collier, Petra Vertes, Tom J. Spencer, Sarah E. Morgan, and Philip McGuire. 2021. “Networks of Transcript Semantics - Netts.”

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

netts-0.2.0rc1.tar.gz (39.5 kB view hashes)

Uploaded source

Built Distribution

netts-0.2.0rc1-py3-none-any.whl (43.8 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page