POTATO: exPlainable infOrmation exTrAcTion framewOrk
This provides a flexible, interpretable tool for researchers and practitioners needing customizable text classification, though it is incremental as it builds on existing graph parsing and rule-based methods.
The authors tackled the problem of building rule-based text classifiers by introducing POTATO, a framework that supports human-in-the-loop learning with graph-based features across multiple languages and domains, resulting in a tool that can be installed via pip and applied in projects such as German legal text and English social media classification.
We present POTATO, a task- and languageindependent framework for human-in-the-loop (HITL) learning of rule-based text classifiers using graph-based features. POTATO handles any type of directed graph and supports parsing text into Abstract Meaning Representations (AMR), Universal Dependencies (UD), and 4lang semantic graphs. A streamlit-based user interface allows users to build rule systems from graph patterns, provides real-time evaluation based on ground truth data, and suggests rules by ranking graph features using interpretable machine learning models. Users can also provide patterns over graphs using regular expressions, and POTATO can recommend refinements of such rules. POTATO is applied in projects across domains and languages, including classification tasks on German legal text and English social media data. All components of our system are written in Python, can be installed via pip, and are released under an MIT License on GitHub.