VILT: Video Instructions Linking for Complex Tasks

TL;DR

This paper introduces VILT, a task of linking instructional videos to complex task steps, demonstrating its effectiveness in improving interactive cooking assistance through a new benchmark, retrieval methods, and user studies.

Contribution

It presents the VILT task, a new benchmark dataset, and evaluates retrieval methods and user experience for linking instructional videos to complex tasks.

Findings

Dense retrieval with ANCE achieves best retrieval performance.

Users learn more effectively with manually linked videos.

Automatically linked videos still significantly aid task learning.

Abstract

This work addresses challenges in developing conversational assistants that support rich multimodal video interactions to accomplish real-world tasks interactively. We introduce the task of automatically linking instructional videos to task steps as "Video Instructions Linking for Complex Tasks" (VILT). Specifically, we focus on the domain of cooking and empowering users to cook meals interactively with a video-enabled Alexa skill. We create a reusable benchmark with 61 queries from recipe tasks and curate a collection of 2,133 instructional "How-To" cooking videos. Studying VILT with state-of-the-art retrieval methods, we find that dense retrieval with ANCE is the most effective, achieving an NDCG@3 of 0.566 and P@1 of 0.644. We also conduct a user study that measures the effect of incorporating videos in a real-world task setting, where 10 participants perform several cooking tasks with varying multimodal experimental conditions using a state-of-the-art Alexa TaskBot system. The users interacting with manually linked videos said they learned something new 64% of the time, which is a 9% increase compared to the automatically linked videos (55%), indicating that linked video relevance is important for task learning.