FLIN: A Flexible Natural Language Interface for Web Navigation

TL;DR

FLIN is a flexible natural language interface that enables web navigation by mapping user commands to concept-level actions, allowing adaptation across different websites without retraining.

Contribution

It introduces a ranking-based approach for web navigation commands that generalizes across websites by focusing on concept-level actions rather than low-level UI interactions.

Findings

FLIN successfully adapts to new websites within the same domain.

The dataset covers nine popular websites across three domains.

FLIN outperforms baseline methods in web navigation tasks.

Abstract

AI assistants can now carry out tasks for users by directly interacting with website UIs. Current semantic parsing and slot-filling techniques cannot flexibly adapt to many different websites without being constantly re-trained. We propose FLIN, a natural language interface for web navigation that maps user commands to concept-level actions (rather than low-level UI actions), thus being able to flexibly adapt to different websites and handle their transient nature. We frame this as a ranking problem: given a user command and a webpage, FLIN learns to score the most relevant navigation instruction (involving action and parameter values). To train and evaluate FLIN, we collect a dataset using nine popular websites from three domains. Our results show that FLIN was able to adapt to new websites in a given domain.