Representing ELMo embeddings as two-dimensional text online
This is an incremental tool for researchers and practitioners working with contextualized embeddings, providing visualization and integration features.
The authors introduced ELMoViz, a new module for the WebVectors toolkit that visualizes ELMo embeddings as two-dimensional text by showing contextually similar words, allowing users to adjust layers and view corpus data. This functionality has been implemented in web services for Russian, Norwegian, and English.
We describe a new addition to the WebVectors toolkit which is used to serve word embedding models over the Web. The new ELMoViz module adds support for contextualized embedding architectures, in particular for ELMo models. The provided visualizations follow the metaphor of `two-dimensional text' by showing lexical substitutes: words which are most semantically similar in context to the words of the input sentence. The system allows the user to change the ELMo layers from which token embeddings are inferred. It also conveys corpus information about the query words and their lexical substitutes (namely their frequency tiers and parts of speech). The module is well integrated into the rest of the WebVectors toolkit, providing lexical hyperlinks to word representations in static embedding models. Two web services have already implemented the new functionality with pre-trained ELMo models for Russian, Norwegian and English.