Bwrite Toolkit manual

Welcome to the manual for the Bwrite Toolkit.

To create an account and start using the Toolkit, create an account.

For beginner users, it’s recommended to start by looking at the Toolkit Glossary and the Toolkit Basics.

Subsections for the currently displayed section will be listed on the right. The subsection titles that are already read will appear gray.

You can go to the previous or next section by using the arrows at the bottom of the screen.

You can access the manual from the menu on the left, but contents are also listed below in more detail:

Contents

• Account Management
  • Creating an Account
  • Logging In
  • Change Password
  • Accessing Projects and Indices
• Toolkit Glossary
• Toolkit Basics
  • Projects
  • Search view
  • Indices
  • Facts
  • Tools and Models
• Use Cases
  • Use Case I: Searching for specific documents using metadata and keywords
  • Use Case II: Analyzing the metadata and common features for a subset of the corpus
  • Use Case III: Adding new metadata
• Bwrite Corpus Overview
  • Accessing Data in Original Form
  • Accessing Data in Sentences
  • How to find the same document in full or in sentences
  • Experiments and Tutorial projects
• Searching
  • Simple Search
  • Advanced Search
  • Searcher Options
  • Search Queries
  • Searching with Metadata
  • Aggregations
• Downloading Data
  • Downloading Document Text
  • Accessing Document PDF
• Adding and Managing Data
  • Creating a New Project
  • Adding Data with the Dataset Importer
  • Reindexing Data
  • Add New Indices to Project
  • Removing an Index from Project
  • Splitting an Index
• Processing Data
  • Lemmatization, Language Detection and Named Entity Recognition (MLP)
  • Language Detection
  • Tokenizing, Stemming and Stripping HTML (ES Analyzer)
• Data Extraction and Classification
  • Lexicons and Embeddings
  • Metadata Extraction and Labeling
  • Keyword Extraction and Tagger Groups
  • Classification
• Tools
  • Editing and Deleting Facts (Facts Manager)
  • Annotating Data
  • Evaluating Model Results
  • Summarizing Text
  • Analyzing Topics
  • Anonymizer
  • Retrieval Augmented Generation
• Workflow Tutorial
  • New project or old?
  • Data validation
  • Create a new Index?
  • Processing
  • Adding Metadata
  • Machine learning workflow
• Troubleshooting
  • I can’t see any projects/add indices to my project
  • Data is not loading or is loading very slowly
  • A task failed
  • F1 score is too high/too low
  • There are too many facts
• For Advanced Users
  • Authentication
  • User Access and Index Management
  • Health
  • Creating a New Index via API
  • Scrolling an Index via API
  • Scrolling an Index into a New Index
  • Fact Structure
  • Script Examples
  • Helpful Links