/logic-rules-sentiment

Code and dataset for our EMNLP 2018 paper "Revisiting the Importance of Logic Rules in Sentiment Classification".

Primary LanguagePython

Logic Rules for Sentiment Classification

This repository contains the code and dataset used in our EMNLP 2018 paper "Revisiting the Importance of Encoding Logic Rules in Sentiment Classification".

You can find the paper on arXiv - https://arxiv.org/abs/1808.07733.

Code

The README for the source code has been added to code/README.md.

Experiments in Section 3.2 were conducted using ZhitingHu/logicnn for a direct comparison with Zhiting Hu's paper, Harnessing Deep Neural Networks with Logic Rules.

Crowdsourced Dataset

The dataset used in the crowdsourcing experiment (Section 5) is contained in crowd-data/sst_crowd_discourse.txt, with details in crowd-data/README.md.

Citation

If you use this code or dataset, please cite:

@inproceedings{KrishnaRevisit2018,
Author = {Kalpesh Krishna and Preethi Jyothi and Mohit Iyyer},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = "2018",
Title = {Revisiting the Importance of Encoding Logic Rules in Sentiment Classification}
}