The labelled training dataset contains 3000 instances, annotated using the ACT platform. The dataset is provided in csv format and contains the following fields:
where citation context represents the sentence containing the citations. Each ciation context in the dataset contains the label, "#AUTHOR_TAG", which represents the citation that is being considered. The citation class labels correspond to values between 0 and 5, where each value represents the following categories:
0 - BACKGROUND
1 - COMPARES_CONTRASTS
2 - EXTENSION
3 - FUTURE
4 - MOTIVATION
5 - USES
The test dataset, in cvs format, contains 1000 instances, with all the above mentioned fields, except labels.
Besides the training and the test sets, we also provide the participants with the full text files corresponding to the coreid's in our dataset. This can be accessed from here. The name of the text files in the full text dump represents the COREID. The participants are encouraged to use this additional information for enhancing the performance of the classifiers. The fulltext for each paper in the dataset is derived from the CORE API.
Any use of the above mentioned full text dataset or additional resources, besides the ACT dataset for this competition should be clearly documented in the short description paper. Also, please make sure, the short paper includes the appropriate references mentioned in this page.