This page provides some information on the structure of the task.
Task
Given two spans of text, determine if both spans were produced by the same author.
Notes
- You are not given the name/ID of either span's author
- You are free to supplement the provided training data
- Both spans are authored in English
- Span length varies
- Spans are joined by the
[SNIPPET]delimiter - This task relates to author profiling, digital stylometry, and authorship identification
Requirements
- Your solution should be reproducible and make use of open source/open weight models and tools
- i.e., Open AI API and models can only be used for dataset augmentation
Labels
This is presented as a binary classification problem. Classify the documents into one of the following categories:
0: Not the same author 1: Same author
Instructions
While you are encouraged to engineer features, you may use any classification algorithm and supplemental data that you like.
Dataset
The majority of data comes from Project Gutenberg.
... supplemented with data aggregated and preprocessed from a variety of other sources 😈