Mapping Natural Language Commands to Web Elements
This addresses the challenge of enabling more intuitive human-computer interaction on the web, but it is incremental as it focuses on a specific domain without broad SOTA impact.
The paper tackles the problem of grounding natural language commands to web elements, such as clicking on specific links or text boxes, by introducing a new task and collecting a dataset of over 50,000 commands that capture phenomena like functional references, relational reasoning, and visual reasoning.
The web provides a rich, open-domain environment with textual, structural, and spatial properties. We propose a new task for grounding language in this environment: given a natural language command (e.g., "click on the second article"), choose the correct element on the web page (e.g., a hyperlink or text box). We collected a dataset of over 50,000 commands that capture various phenomena such as functional references (e.g. "find who made this site"), relational reasoning (e.g. "article by john"), and visual reasoning (e.g. "top-most article"). We also implemented and analyzed three baseline models that capture different phenomena present in the dataset.