Direct parsing to sentiment graphs

David Samuel, Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid and Erik Velldal

University of Oslo, Language Technology Group
University of the Basque Country UPV/EHU, HiTZ Center – Ixa
National Library of Sweden, KBLab

Paper
Pretrained models
Interactive demo on Google Colab

---

This repository provides the official PyTorch implementation of our paper "Direct parsing to sentiment graphs" together with pretrained base models for all six datasets (TODO): Darmstadt, MPQA, Multibooked_ca, Multibooked_eu and NoReC.

---

How to run

🐾   Training

To train PERIN on NoReC, run the following script. Other configurations are located in the perin/config folder.

cd perin
sbatch run.sh config/seq_norec.yaml

🐾   Inference

You can run the inference on the validation and test datasets by running:

python3 inference.py --checkpoint "path_to_pretrained_model.h5" --data_directory ${data_dir}

Citation

@inproceedings{samuel-etal-2022-direct,
    title = "Direct parsing to sentiment graphs",
    author = "Samuel, David  and
      Barnes, Jeremy  and
      Kurtz, Robin  and
      Oepen, Stephan  and
      {\O}vrelid, Lilja  and
      Velldal, Erik",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-short.51",
    doi = "10.18653/v1/2022.acl-short.51",
    pages = "470--478",
    abstract = "This paper demonstrates how a graph-based semantic parser can be applied to the task of structured sentiment analysis, directly predicting sentiment graphs from text. We advance the state of the art on 4 out of 5 standard benchmark sets. We release the source code, models and predictions.",
}