StreamSide: A Fully-Customizable Open-Source Toolkit for Efficient Annotation of Meaning Representations
It provides a customizable tool for researchers and practitioners in natural language processing to efficiently annotate semantic data, though it is incremental as it builds on existing annotation frameworks.
The paper introduces StreamSide, an open-source toolkit for annotating various meaning representations, supporting multiple annotation schemes, input formats, and both sentence- and document-level annotation.
This demonstration paper presents StreamSide, an open-source toolkit for annotating multiple kinds of meaning representations. StreamSide supports frame-based annotation schemes e.g., Abstract Meaning Representation (AMR) and frameless annotation schemes e.g., Widely Interpretable Semantic Representation (WISeR). Moreover, it supports both sentence-level and document-level annotation by allowing annotators to create multi-rooted graphs for input text. It can open and automatically convert between several types of input formats including plain text, Penman notation, and its own JSON format enabling richer annotation. It features reference frames for AMR predicate argument structures, and also concept-to-text alignment. StreamSide is released under the Apache 2.0 license, and is completely open-source so that it can be customized to annotate enriched meaning representations in different languages (e.g., Uniform Meaning Representations). All StreamSide resources are publicly distributed through our open source project at: https://github.com/emorynlp/StreamSide.