Infosense image

InfoSense

InfoSense is a research lab in the Department of Computer Science, Georgetown University. We research Artificial Intelligence (AI), Information Retrieval (IR), Machine Learning (ML), and Privacy.


We care about how people seek and process “information” and make “sense” out of it, with the assistance of AI and hopefully in a privacy-preserving manner.


Formed by undergraduates, Masters, Ph.Ds., Post-docs, programmers and faculty, the research team devote our passion and energy into both theory and systems development of human-centered AI.

Search Engines as Bots image

Search Engines as Bots

Search engines are perhaps the most successful application that has changed how people seek information and acquire knowledge. We view search engines as intelligent bots who interact with human users and provide answers to them. In the meantime, you might only see lists of relevant documents being returned to the user. However, as AI and search engine researchers, we envision a much richer mode of interaction between humans and search engines. Essentially, search engines, which already serve this role in the current primitive form, will continue to be bots that assist humans to find answers. The range of interaction, communication, and mutual growth between the two would cover collaboratively finishing a task (e.g. collecting information and making decisions to purchase a home), exploring an unknown knowledge field, life-long learning, and many more. The key distinguishing feature of search engines from other AI fields is that we will always have humans in-the-loop. The human plays an important roles in our research and the search engines will always centrally focus on human users.

Dynamic Search image

Dynamic Search

When a search engine interacts with a human user, both enter a series of dynamically changing states. Governed by the goal of satisfying the user’s information need, dynamic search aims to statistically model this information seeking process. Dynamic search identifies itself from ad-hoc search and relevance feedback models by admitting and handling the temporal dependency among individual searches and assuming a long-term goal that focuses on accomplishing a task (in contrast to killing time by being entertained with a chatbot).


Here, the user and the search engine form a partnership to explore the possible information space to find documents that are rewarding. The family of reinforcement learning (RL) methods fit well into this trial-end-error setting. Thus, much of our effort is inspired by, but not directly derived from, reinforcement learning. Ultimately, we focus on bridging understanding of human users, where the Information Retrieval (IR) community is strong, and mathematical modelings of dynamic systems that excite a wide audience in artificial intelligence and machine learning.

New interfaces image

New Interfaces

For a long period of time, a search engine interface was equivalent to a query box and 10 blue links. We are not in a position to judge its effectiveness, nor aesthetic value. But we are skeptical that the lack of innovation in forms of user inputs indicates that this represents the apex of search engine user interface performance.


In our Lab, we experiment and study new types of interfaces for information seeking and sense-making. We appply novel mathematical algorithms and experiment equipping human users with virtual reality (VR), augmented reality (AR), voice input, and smart glasses. We are interested in discovering new and more natural interactions between humans and machines, with an enduring focus on how these new interfaces would enhance the algorithms’ effectiveness.

Domain-Specific Search image

Domain-Specific Search

Search engines are not always for the web. There are many more in-house search engines built on top of offline documents to serve domain-specific purposes. Classical search engine models, such as the vector space model, BM25, language models, and learning-to-rank methods, supply a basic but highly effective set of methods and off-the-shelf tools for practitioners to build in-house search engines. The users of these domain-specific search engines are usually professional searchers, including law enforcement officers, patent examiners, lawyers, physicians, and writers, who have demands of unique search functionality to facilitate their in-depth investigations and analysis. The searches are usually more complex, take longer and require flexible and reliable switching between collection browsing, keyword search, and structured search. In the past, we have worked on domains such as prior arts, dark web, human-trafficking, illicit goods, counterfeit electronics, and disease controls. In the future, we expect to explore new demands from a variety of domains for the greater good.

Evaluation image

Evaluation

Evaluation gives an idea of how well or poorly a system works. Evaluations can be manual or based on testbeds and metrics - Our Lab is experienced in the latter. We have organized or helped with evaluations for the National Institute of Standards and Technology (NIST), Defense Advanced Research Projects Agency (DARPA), and U.S. Patent and Trademark Office (USPTO). A complete campaign of search engine evaluation involves defining tasks, providing standard datasets, collecting human annotations, designing the evaluation schemes and metrics and managing the participation.


Although we need to do all of above, our Lab primarily focuses on the scientific aspect of an evaluation. We design human-centric evaluation metrics that model complex user behavior in the metric itself. We also investigate how these metrics act as optimization objectives for the machine learning algorithms. Conducting evaluation campaigns is hard work but definitely a rewarding experience.

Privacy image

Privacy

Privacy and personalization seem naturally opposed. While users enjoy personalized services from search engines, recommender systems, social media, transportation, and deliveries, they grant those companies entrance to their personal life without a complete understanding of the risks. Privacy has become a battlefield for the governments, the companies, the innocent users, and competitors of those companies including small businesses and professors. As academic researchers, we cannot change the current policies, but we can research and improve the situation from the technical perspective.


Our Lab is interested in creating privacy-preserving information retrieval algorithms that would perform information seeking tasks while protecting users’ privacy. We are also interested in revealing privacy risks to the users before they submit any data to the companies. Ultimately, we hope to help every user manage their own data and deserved services, breaking the curse of centralized data ownership.

News

  • 2024 Jan
    Prof. Grace Hui Yang is the General Co-Chair for SIGIR 2024! Welcome to D.C.!
  • 2023 Feb
    Zhiwen Tang (graduated Aug 2021) joined Yunnan University as Associate Professor.
  • 2021 Feb
    Summer 2021 projects: http://infosense.cs.georgetown.edu/opportunities.html
  • 2019 Nov
    Our group has one paper accepted by AAAI 2020 as oral presentation. Congratulations!
  • 2019 Oct
    Our group has 2 workshop papers accepted by NeurIPS 2019. See you in Vancouver, Canada!
  • 2019 Feb
    InfoSense hosted Professor Ming Zhang from Peking University . Professor Zhang presented her work on LEARNING THE JOINT REPRESENTATION OF HETEROGENEOUS TEMPORAL EVENTS FOR CLINICAL ENDPOINT PREDICTION . The paper was originally presented at AAAI 2018 and can be found here .
  • 2019 Feb
    Congratulations to Grace. She was recognized as WSDM 2018 Outstanding Senior Reviewer!
  • 2018 Sep
    Welcome Geoff to join our group!
  • 2017 Oct
    Sicong successfully defended his Ph.D. thesis! Congratulations!!
  • 2017 Oct
    Zhiwen won the Best Student Paper Award at ICITR 2017 for our paper "Investigating Per Topic Upper Bound for Session Search Evaluation". Congratulations!
  • 2017 Oct
    Our group has 2 full papers, 1 short papers and 1 tutorial presented at ICTIR 2017, Amsterdam. Nice work team!
  • 2017 May
    Welcome Amy, Shuchen, and Chong to join our group!
  • 2016 June
    Grace's Book on "Dynamic IR Modeling" is published!
  • 2016 June
    Welcome Jianxian and Lingqiong to join our group!
  • 2016 May
    Congratulations!! Hongkai's thesis is successfully defended!
  • 2016
    Welcome Yunyun Chen, Angela Yang, Susan Bhattarai, Joshua Kang, Simeon Meerson and Christopher Zawora join our research group!
  • 2015
    Welcome Hongkai Wu join our research group!
  • 2014
    Welcome Jie Zhou join our research group!
  • 2014
    Grace introduced Dynamic Domain Track in the 2014 TREC workshop. (download ppt here).
  • 2014
    Grace will co-organize the TREC 2015 Dynamic Domain Track with John Frank and Ian Soboroff.
  • 2014
    Welcome Shiqi Liu join our research group!
  • 2014
    Our group has 1 full paper, 1 short paper and 1 demo paper accepted by SIGIR 2014. Congratulations, Jiyun, Sicong and Chris!
  • 2014
    Grace will give the Dynamic Information Retrieval Modeling Tutorial in SIGIR 2014, with Marc Sloan and Jun Wang.
  • 2014
    Grace co-chairs the first Privacy-Preserving IR workshop PIR 2014 co-located with SIGIR 2014.
  • 2014
    Grace co-chairs SIGIR 2014 Doctoral Consortium with Shane Culpepper.
  • 2013
    Our group won the 1st position in TREC 2013 Contextual Suggestion (ClueWeb). Congratulations, Jiyun!
  • 2013
    Our group won the 1st position in TREC 2013 Contextual Suggestion (ClueWeb). Congratulations, Jiyun!
  • 2013
    New class for Fall 2013 - COSC289 Multimedia Processing. Take it if you want to know how to play with images, audios, and video files by only using simple programming skills such as Arrays and File operators.
  • 2013/6
    Our group won the 1st position in patent prior art retrieval evaluation in CLEF-IP 2013. Congratulations, Jiyun!
  • 2013/4
    Our group has 1 full, 1 short, and 1 demo paper accepted by SIGIR 2013. Congratulations, Dongyi, Sicong, and Jiyun!
  • 2013/4
    Our full paper "Utilizing Query Change for Session Search" is accepted by SIGIR 2013. Congratulations, Dongyi and Sicong!