Kris Hammond

Professor of Electrical Engineering and Computer Science

Prior to joining the faculty at Northwestern, Kris founded the University of Chicago’s Artificial Intelligence Laboratory. His research has been primarily focused on artificial intelligence, machine-generated content and context-driven information systems. Kris currently sits on a United Nations policy committee run by the United Nations Institute for Disarmament Research (UNIDIR). He received his PhD from Yale.

Projects

Projects Kris Hammond has worked on.

Automated Fact Checking

There's more information than ever, and often, the audience is left wondering whether they should trust what they hear. What systems could we build that help people simply answer the question, "is that true?"

Conversational Interface for News

Using a combination of raw search and the collections of regular expressions, build a system that would allow a user to ask questions about what is happening in the news and get back answers and pointers to sources. In the vein of Watson, multiple approaches to matching against text for different types of questions would be used to find answers.  This is envisioned as text (rather than voice) driven system.

DocumatAutomated Documentary Shorts

What would it take to automatically create a brief documentary about someone’s life? For this project, we’ll try to do just that. Given a biographical document (for example, a person’s Wikipedia page), can we extract key facts of their life, search the internet for still images that might illustrate those facts, and compose a brief video clip that puts together text (converted to speech) and images? We’ll do as much of it as we can in ten weeks, and if work is promising, continue in a future Knight Lab Studio session.

Fact FlowEfficiency for editing. Credibility and trust for publishing

Editorial fact-checking is a mess at best and readers don't see the benefits. Typically they doubt it happens or don't appreciate the work it takes to make it happen. On the editing side, almost everyone who does it uses an antiquated process derived from print production habits even though most writers and editors are drafting in Google Docs. This can be better. Let's make it better for both editorial and readers!

Recognizing Bias in the News

Over the past few years, we have seen increased attention to the problem of bias. AI systems built on a substrate of machine learning are increasingly being seen as biased. Automated information delivery systems (e.g., Facebook, twitter) are using algorithms that, by their nature, are biased in the type of news they recommend. And we now have an entire class of language models constructed using millions of documents that are demonstrably biased. One could argue that bias is impossible to avoid but this project is an attempt to do so.

Story for YouWriting stories for people who don’t want to read them

Studies have shown that people on opposing sides of political issues use fundamentally different language to discuss their views. One of the effects of this is that people living in News Filter Bubbles can immediately notice and then discard stories that use the terms associated with their opposition.

Talking to Data

The aim of this project is to provide users with a conversational interface to data sets that allow them to first describe what the data is about, where the various elements that they can ask about can be found, and then ask questions about the data.

Watch Me WorkSearch driven by your own writing

As we work, we often need information to support our thinking. This often requires turning away from the work, pulling up an engine and then typing in a query. If you are writing, however, the queries that we need are already embedded in the text of the document we are authoring.

Zoom to an AnswerConsidering Zoom as a conduit for information

As we settle into the new world of Zoom, Meet and Teams, it is clear that even when the dust clears, these platforms are not going away. Each is developing its own feature set, but few are focused on the idea that we now can capture interaction information at a more detailed level and with a better signal to noise ratio than we were able to do in face to face meetings. Exploiting both these features, ubiquitous use of Zoom and its siblings and the information we can pull out of them, we would like to consider what it might mean for Zoom to be a conduit for information. In particular, how can we use the Zoom APIs to access information requests (bios, company profiles, general search) that leverage both the specific requests and the shared context.