Rosette Adaptation Studio is a web-based tool. Your site administrator can provide you with the web address of your installation, user id, and password.
Note
Chrome and Firefox are the supported browsers for Rosette Adaptation Studio.
When you log in to Adaptation Studio, you'll see the global navigation bar with the following options:
All Projects: Lists the projects you have access to. Superusers will see all projects on the server. Managers see the projects they have created or are assigned to. Annotators and adjudicators see the projects they are assigned to.
New Project: Allows managers or superusers to create new projects or import existing projects.
Events Schema Template: Allows managers or superusers to add, modify, or export schema templates for event extraction.
User Management: Allows superusers to add, modify, or delete users.
Help: Select Help from the dropdown menu to open this guide in a new tab. Select About from the dropdown menu to view version and copyright information.
Under the navigation bar is a status bar showing the state of the servers as well as your license expiration date.
All projects you have authorization to access are listed. Superusers have access to all projects on the server.
Selecting your username in the upper-right corner of Adaptation Studio expands the user menu. The user menu displays the following information and options:
The email address associated with your profile
Your user type
Settings: Edit your profile name, email address, or password. See Edit User.
Logout: Log out of Adaptation Studio.
Each user can edit their personal information, including changing their password.
Select your username in the upper right corner of Adaptation Studio.
Select Settings from the dropdown menu.
Edit any of the fields except for the role. Only the superuser can update an individual's role.
Select Update.
Select on a project to access the dashboard for that project. The dashboard displays the current state of the project and provides access to project-related tasks. Your user type will determine the information displayed and the tasks you can perform.
Common tasks are accessed from the project navigation bar on the bottom of the dashboard. Less-frequent tasks are accessed from the project (hamburger) menu in the upper right-hand corner of the project dashboard. Some tasks, such as Delete, are only available in the All Projects view.
Project navigation bar options
The options displayed on the project navigation bar depend on the type of project. Whether an option is active depends on whether your user type has permissions to perform that option. For example, if you are an annotator on a project, the Manage option will not be active.
Project Schema: (Events only) Modify a template schema for the project.
Add Documents: Upload documents for annotation.
Annotate: Annotate assigned documents.
Adjudicate: Review annotations and resolve differences between annotators.
View Annotations: View samples based on assignment and status.
Test Document: See how the model will perform on a sample text. Enter short text and view the model's current predictions.
Manage: Access manager tasks.
Reports: View annotation progress, adjudication progress, and inter-annotator agreement statistics.
When you log into Rosette Adaptation Studio, you will be one of the following types of users:
Superuser: Creates users in addition to all other tasks.
Manager: Creates and manages new projects.
Adjudicator: Reviews annotations by multiple users and settles conflicts when samples are annotated differently.
Annotator: Annotates samples from documents in one or more projects.
Each user type has all permissions of the users below them on the list. For example, a manager has access to all adjudicator and annotator permissions.
To add and manage users, select User Management (superuser only).
Note
You must be registered as a superuser. Only a superuser can add new users. The superuser can access and manage all projects.
Once Rosette Adaptation Studio is installed and running, go to User Management to create users.
Select User Management from the global navigation bar.
Select Add user to create an id for each user. Assign a role to each user.
Important
The initial superuser password for Rosette Adaptation Studio is set on install and must be changed on first login.
The superuser can create users and perform all tasks. At install, the superuser is set to admin.
The first time you log in as admin, you will be forced to change the password. The initial login information is:
Name: admin
Password: admin
The superuser password can be reset by running the reset_admin.sh in /basis/ras/scripts. After reset, you will be prompted to change the password when you log in the first time.
Note
If the superuser password contains the special characters $ or \, the password must be in quotes when sent to the reset_admin.sh script. Example:
./reset_admin.sh '2^$4bu\Qm$4C'
When using the headless installer, you can set the initial superuser password in the properties file.
To override the admin password, set the admin_password property to the plain text password to use in the install-ras-headless.properties file. On install, this password will be hashed and inserted into the authentication database of RAS. Once installed the value can be deleted from the properties file.
You will not be prompted to change the password on the first login.
Active learning is a form of supervised machine learning in which the learning algorithm guides the order of samples presented to the annotator. This can lead to significant reductions in annotation time and expense.
Active learning accelerates the annotation process in two ways:
It presents the most uncertain sample for annotation, ensuring that the next sample you annotate will provide the most useful annotations.
The engine provides its best guess or prediction for an annotation, where possible.
When you upload a document, it is divided into samples for annotation. A document is made up of multiple samples, where each sample is a sentence in the document. The active learning module selects the "best" document for annotation. The best document is the one which has the lowest certainty for predicting annotations.
Active learning can ensure that samples containing unique or uncommon terms are annotated early in the process. Each time a sample is completed, the engine looks for the sample with the lowest confidence, that is, the sample that is the most unfamiliar to the system. By selecting the unfamiliar samples, Annotation Studio reduces skewing of results towards more common and represented terms.
Tip
Annotators must be careful to review suggested annotations, especially early in the annotation process, when they are more error-prone. You may want to suppress these suggestions to avoid biasing the human annotators. Set the configuration option Hide Eval Predictions to suppress suggested annotations for samples in the evaluation set. Suggestions are still displayed for the training set.
Annotation is a process of assigning labels to parts of documents. The set of labels, as well as the words or parts of words assigned to the label, depends on the type of annotation task.
-
For named entity recognition (NER), the labels are the entity types the model is being trained to extract. REX has a set of predefined entity types, defined by language. They are automatically defined when the project is created.
Note
If Use Basis Training Data was enabled during initial project configuration, you cannot add new labels to the project.
For events, the labels are the key phrase and the roles. They are defined by the schema.