metadata
license: apache-2.0
language:
- 'no'
pipeline_tag: token-classification
model-index:
- name: SSA-Perin
results:
- task:
type: structured sentiment analysis
dataset:
name: NoReC
type: NoReC
metrics:
- name: Unlabeled sentiment tuple F1
type: Unlabeled sentiment tuple F1
value: 44.12%
- name: Target F1
type: Target F1
value: 56.44%
- name: Relative polarity precision
type: Relative polarity precision
value: 93.19%
This repository contains a pretrained model (and an easy-to-run wrapper for it) for structured sentiment analysis in Norwegian language, pre-trained on the NoReC_fine dataset. This is an implementation of the method described in
@misc{samuel2022direct,
title={Direct parsing to sentiment graphs},
author={David Samuel and Jeremy Barnes and Robin Kurtz and Stephan Oepen and Lilja Øvrelid and Erik Velldal},
year={2022},
eprint={2203.13209},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
The main repository that also contains the scripts for training the model, can be found on the project github. The model is also available in the form of a HF space.
The sentiment graph model is based on an underlying masked language model – NorBERT 2. The proposed method suggests three different ways to encode the sentiment graph: "node-centric", "labeled-edge", and "opinion-tuple". The current model
- uses "labeled-edge" graph encoding
- does not use character-level embedding
- all other hyperparameters are set to default values , and it achieves the following results on the held-out set of the dataset:
| Unlabeled sentiment tuple F1 | Target F1 | Relative polarity precision |
|---|---|---|
| 0.434 | 0.541 | 0.926 |
The model can be easily used for predicting sentiment tuples as follows:
>>> import model_wrapper
>>> model = model_wrapper.PredictionModel()
>>> model.predict(['vi liker svart kaffe'])
[{'sent_id': '0',
'text': 'vi liker svart kaffe',
'opinions': [{'Source': [['vi'], ['0:2']],
'Target': [['svart', 'kaffe'], ['9:14', '15:20']],
'Polar_expression': [['liker'], ['3:8']],
'Polarity': 'Positive'}]}]