Frame-Semantic and PropBank Semantic Role Labeling with Syntactic Scaffolding.
Switch branches/tags
Nothing to show
Clone or download
swabhs Update scaffolded_fsp.json
Remove xavier_normal init
Latest commit e664077 Nov 3, 2018

Scaffolding: Syntactic Scaffolds for Semantic Structures

A repository based on the EMNLP 2018 paper for Frame-Semantic and PropBank Semantic Role Labeling with Syntactic Scaffolding. Code for coreference with a syntactic scaffold coming soon.


This repository was built on an earlier version of AllenNLP. Due to changes in the API, we recommended installing directly via steps below (adapted from the AllenNLP installation), as opposed to using an installed version of AllenNLP.

  1. Download and install Conda.

  2. Create a Conda environment with Python 3.6

    conda create -n scaffold python=3.6
  3. Activate the Conda environment. (You will need to activate the Conda environment in each terminal in which you want to use AllenNLP.

    source activate scaffold
  4. Install in your environment

    git clone
  5. Change your directory to where you cloned the files:

    cd scaffolding/
  6. Install the required dependencies.

    INSTALL_TEST_REQUIREMENTS="true" ./scripts/
  7. Install PyTorch version 0.3 via pip (modify based on your CUDA environment). Conda-based installation results in slower rutime because of a CUDA issue.

    pip install

Step 1: Get Data

Download FN data and place it under a data/ directory under the root directory.

Step 2: Get Pre-trained Models

Frame-SRL baseline

Frame-SRL scaffold with common non-terminals

PropBank SRL baseline

PropBank SRL scaffold with common non-terminals

Step 3: Test

python -m evaluate \
    --archive-file log_final_pb_baseline/model.tar.gz \
    --evaluation-data-file data/fndata-1.5/test/fulltext/ \
    --cuda-device 0

Coming Soon: For the syntactic scaffold model for PropBank SRL, use the pbscaf branch:

git checkout pbscaf

and then run evaluation as above.


For scaffolds, use $command=train_m and for baselines, $command=train.

python -m $command training_config/$config --serialization-dir log


Paper coming soon on ACL Anthology / ArXiv.

    author      = {Swabha Swayamdipta and Sam Thomson and Kenton Lee and Luke Zettlemoyer and Chris Dyer and Noah A. Smith},
    title       = {Syntactic Scaffolding for Semantic Structures},
    booktitle   = {Proc. of EMNLP},
    url         = {},
    year        = {2018}