Videos
See AI2's full collection of videos on our YouTube channel.
Natural Language Understanding for Events and Participants in Text
May 6, 2019 | Rachel RudingerConsider the difference between the two sentences “Pat didn’t remember to water the plants” and “Pat didn’t remember that she had watered the plants.” Fluent English speakers recognize that the former sentence implies that Pat did not water the… more
Understanding question comprehension, and generalizability
May 2, 2019 | Pramod Kaushik MudrakartaWe present two results: 1) Analysis techniques for state-of-the-art question-answering models on images, tables and passages of text. We show how these networks often ignore important question terms. Leveraging such non-robust behavior, we present… more
Augmenting Collective Human Work
May 1, 2019 | Jonathan BraggA longstanding goal of artificial intelligence (AI) is to develop agents that can assist or augment humans. Such agents have the potential to transform society. While AI agents can excel at well-defined tasks like games, much more limited progress… more
Both Sides Now: Generating and Understanding Visually-Grounded Language
April 24, 2019 | Peter AndersonFrom robots to cars, virtual assistants and voice-controlled drones, computing devices are increasingly expected to communicate naturally with people and to understand the visual context in which they operate. In this talk, I will present our latest… more
User-centric Recommendation Models and Systems
April 12, 2019 | Longqi YangThe daily actions and decisions of people are increasingly shaped by recommendation systems, from e-commerce and content platforms to education and wellness applications. These systems selectively suggest and present information items based on their… more
Learning Challenges in Natural Language Processing
April 8, 2019 | Swabha SwayamdiptaAs the availability of data for language learning grows, the role of linguistic structure is under scrutiny. At the same time, it is imperative to closely inspect patterns in data which might present loopholes for models to obtain high performance… more
Learning Structured Information from Language
April 3, 2019 | Arzoo KatiyarExtracting information from text entails deriving a structured, and typically domain-specific, representation of entities and relations from unstructured text. The information thus extracted can potentially facilitate applications such as question… more
Natural Language Understanding with Indirect Supervision
March 29, 2019 | Daniel KhashabiCan we solve language understanding tasks without relying on task-specific annotated data? This could be important in scenarios where the inputs range across various domains and it is expensive to create annotated data. I discuss two different… more
Spatiotemporal understanding of people using scenes, objects and poses
March 11, 2019 | Rohit GirdharHumans are arguably one of the most important entities that AI systems would need to understand to be useful and ubiquitous. From autonomous cars observing pedestrians, to assistive robots helping the elderly, a large part of this understanding is… more
AI & Policy Workshop
March 7, 2019 |"An Ethical Crisis in Computing?" Moshe Vardi | Karen Ostrum George Distinguished Professor, Computational Engineering, Rice University "Algorithmic Accountability: Designing for Safety" Ben Shneiderman | Distinguished Professor, Department of… more