## Description

This competition is a part of the shared task hosted within the third workshop on Scholarly Document Processing ([SDP 2022](https://sdproc.org/2022/)), being held in association with the 29th International Conference on Computational Linguistics ([COLING 2022](https://coling2022.org/)).

## Competition report 

**Yury Kashnitsky, Drahomira Herrmannova, Anita de Waard, George Tsatsaronis, Catriona Catriona Fennell, and Cyril Labbe. 2022. [Overview of the DAGPap22 Shared Task on Detecting Automatically Generated Scientific Papers](https://aclanthology.org/2022.sdp-1.26/). In Proceedings of the Third Workshop on Scholarly Document Processing, pages 210–213, Gyeongju, Republic of Korea. Association for Computational Linguistics.**

There are increasing reports that research papers can be written by computers, which presents a series of concerns (e.g., see [1]). In this challenge, we explore the state of the art in detecting automatically generated papers. We frame the detection problem as a binary classification task: given an excerpt of text, label it as either human-written or machine-generated. We provide a corpus of over 5000 excerpts from automatically written papers, based on the work by Cabanac et al. [2], as well as documents collected by Elsevier publishing and editorial teams. As a control set, we provide a 5x larger corpus of openly accessible human-written as well as generated papers from the same scientific domains of documents. We also encourage contributions that aim to extend this dataset with other computer-generated scientific papers, or papers that propose valid metrics to assess automatically generated papers against those written by humans.

## Data

Check out the [Data](https://www.kaggle.com/competitions/detecting-generated-scientific-papers/data) tab for the description of the provided data. The competition allows the use of external data, so feel free to augment the training set with generated content coming from generator/summarizer/paraphrazer and other Deep Learning models.

## Baseline

Check out the [Tf-Idf & logistic regression baseline](https://www.kaggle.com/code/kashnitsky/fake-papers-tf-idf-logistic-regression-baseline/) for the task in hand.

## Rules

Check out the [Rules](https://www.kaggle.com/competitions/detecting-generated-scientific-papers/rules) tab, in particular, it mentions the SDP workshop timelines. 


## Acknowledgements

We thank Cyril Labbé, Basile Dubois-Binnaire, Guillaume Cabanac, and Alexander Magazinov for their input in the ideation phase of the task preparation. 

## Links
[1] Holly Else. (2021). ["'Tortured phrases' give away fabricated research papers."](https://www.nature.com/articles/d41586-021-02134-0) Nature.
[2] Guillaume Cabanac, Cyril Labbé, and Alexander Magazinov. (2021). ["Tortured phrases: A dubious writing style emerging in science. Evidence of critical issues affecting established journals."](https://arxiv.org/abs/2107.06751)