Skip to content

Latest commit

 

History

History
24 lines (19 loc) · 1.38 KB

readme.md

File metadata and controls

24 lines (19 loc) · 1.38 KB
Raw

Purpose

The parser provided in this package is an implementation of the t5-small parser with language model head for conditional generation.

The semantic parsing task: converting natural language commands -> The Unified Meaning Representation (UMRF). This format powers the TeMoto2.0 packaged developed by the University of Tartu and University of Texas at Austin.

How to Install

  1. clone this repository into your ~/catkin_ws/src
  2. Download the model and tokenizer from [email protected] 's google drive (please contact author of this git repo for access)
  3. from ~/catkin_ws/src/ROS1_UMRF_T5Parser/scripts run pip install -r requirements.txt
  4. Extract the zip in your download then place the saved_model and saved_tokenizer at the same directory level as the umrf_parser.py

How to Use

  1. No .launch is included
  2. source your workspace
  3. start roscore in a terminal
  4. navigate to ~/catkin_ws/src/ROS1_UMRF_T5Parser/scripts
  5. python3 umrf_parser.py

This will being running the node. The node listens to natural language commands on the rostopic : umrf_parses. The UMRF outputs are published on umrf_parses_output.

Future Work

  1. Provide a RoboFrameNet Parser
  2. Implement online learning model for live UMRF corrections