Search results

This is our first time participating in any Alexa competition and we are excited to tackle the problems facing Alexa in the domains of cooking and do-it-yourself tasks.

Our ambition is to move AI and search closer to the way humans communicate and solve tasks.

The team’s vision is to provide an enjoyable user experience with professional step-by-step instructions on cooking and DIY tasks by leveraging a rich task-knowledge base, multi-modal interactions, user personalisation, and human-like fluency.

Sneha Rajana is an applied scientist at Amazon today, but she didn't start out that way. Learn how she made the switch, and the advice she has for others considering a similar change.

The University of Pennsylvania team consists of talents with a variety of expertise. We propose to design QuakerBot that can guide users through tasks in a wide variety of domains, like those in WikiHow or Youtube tutorial videos.

From beautiful Santa Barbara, California we are team GauchoBot.

Manual debugging is a common productivity drain in the machine learning (ML) lifecycle. Identifying underperforming training jobs requires constant developer attention and deep domain expertise. As state-of-the-art models grow in size and complexity, debugging becomes increasingly difficult. Just as unit tests boost traditional software development, an automated ML debugging library can save time and money

Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem consisting of step-by-step natural language instructions to achieve subgoals which compose to an

Applied Scientist

Constructed-response questions (CRQs) are an important activity that can help foster generative processing and promote a deeper understanding of the core content for learners. However, providing feedback and grading free-form text responses is labor intensive. This paper proposes a novel solution for providing targeted feedback automatically in online learning environments without any model training process

New approach to few-shot learning improves on state of the art by combining prototypical networks with data augmentation.

Learn more about Team TacoBot from Ohio State University, competing in the first Alexa Prize TaskBot Challenge.

Team Tartan is a mix of software engineers, linguistics researchers, product managers and human-computer interaction designers.

Our vision is to build a socialbot that can really “understand” the conversation as well as the context in which the conversation is being carried out, just like humans do.

We are proud of living in the country where the word “robot” was first used in the play called R.U.R. written by Karel Capek.

This article describes a style of applying symbolic model checking developed over the course of four years at Amazon Web Services (AWS). Lessons learned are drawn from proving properties of numerous C-based systems, for example, custom hypervisors, encryption code, boot loaders, and an IoT operating system. Using our methodology, we find that we can prove the correctness of industrial low-level C-based