Logo: University of Southern California

Events Calendar



Select a calendar:



Filter March Events by Event Type:



Events for March 04, 2021

  • CS Colloquium: Huda Khayrallah (John Hopkins University) - Machine Translation for All: Improving Machine Translation in Low Resource, Domain Mismatch & Noisy Training Settings

    Thu, Mar 04, 2021 @ 09:00 AM - 10:00 AM

    Computer Science

    Conferences, Lectures, & Seminars


    Speaker: Huda Khayrallah, John Hopkins University

    Talk Title: Machine Translation for All: Improving Machine Translation in Low Resource, Domain Mismatch & Noisy Training Settings

    Series: CS Colloquium

    Abstract: Machine translation uses machine learning to automatically translate text from one language to another and has the potential to reduce language barriers. Recent improvements in machine translation have made it more widely-usable, partly due to deep neural network approaches. However-”like most deep learning algorithms-”neural machine translation is sensitive to the quantity and quality of training data, and therefore produces poor translations for some languages and styles of text. Machine translation training data typically comes in the form of parallel text-”sentences translated between the two languages of interest. Limited quantities of parallel text are available for most language pairs, leading to a low-resource problem. Even when training data is available in the desired language pair, it is frequently formal text-”leading to a domain mismatch when models are used to translate a different type of data, such as social media or medical text. Neural machine translation currently performs poorly in low-resource and domain mismatch settings; my work aims to overcome these limitations, and make machine translation a useful tool for all users.

    In this talk, I will discuss a method for improving translation in low resource settings-”Simulated Multiple Reference Training (SMRT; Khayrallah et al., 2020)-”which uses a paraphraser to simulate training on all possible translations per sentence. I will also discuss work on improving domain adaptation (Khayrallah et al., 2018), and work on analyzing the effect of noisy training data (Khayrallah and Koehn, 2018).

    This lecture satisfies requirements for CSCI 591: Research Colloquium


    Biography: Huda Khayrallah is a PhD candidate in Computer Science at The Johns Hopkins University where she is advised by Philipp Koehn. She is part of the Center for Language and Speech Processing and the machine translation group. She works on applied machine learning for Natural Language Processing, primarily machine translation. Her work focuses on overcoming deep learning's sensitivity to the quantity and quality of the training data, including low resource and domain adaptation settings. In Summer 2019, she was a research intern at Lilt, working on translator-in-the-loop machine translation. She holds an MSE in Computer Science from Johns Hopkins (2017), and a BA in Computer Science from UC Berkeley (2015). More info about her can be found on her website: http://www.cs.jhu.edu/~huda

    Host: Xiang Ren

    Audiences: Everyone Is Invited

    Posted By: Assistant to CS chair

    OutlookiCal
  • NL Seminar-LIGHT: Training agents that can act and speak with other models and humans in a rich text adventure game world

    Thu, Mar 04, 2021 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Jason Weston , Fair/NYU

    Talk Title: LIGHT: Training agents that can act and speak with other models and humans in a rich text adventure game world

    Series: NL Seminar

    Abstract: LIGHT is a rich fantasy text adventure game environment featuring dialogue and actions between agents in the world, which consist of both models and humans. I will summarize work on building this research platform, including crowdsourcing and machine learning to build the rich world environment, training agents to speak and act within it, and deploying the game for lifelong learning of agents by interacting with humans. See
    LIGHT Learning in Interactive Games with Humans and Text. The LIGHT project is a large scale fantasy text adventure game research platform for training agents that can both talk and act, interacting either with other models or with humans.
    parl. ai and the talk! for more.



    Biography: Jason Weston is a research scientist at Facebook, NY and a Visiting Research Professor at NYU. He earned his PhD in machine learning at Royal Holloway, University of London and at AT and T Research in Red Bank, NJ advisors: Alex Gammerman, Volodya Vovk and Vladimir Vapnik in 2000. From 2000 to 2001, he was a researcher at Biowulf technologies. From 2002 to 2003 he was a research scientist at the Max Planck Institute for Biological Cybernetics, Tuebingen, Germany. From 2003 to 2009 he was a research staff member at NEC Labs America, Princeton. From 2009 to 2014 he was a research scientist at Google, NY. His interests lie in statistical machine learning, with a focus on reasoning, memory, perception, interaction and communication. Jason has published over 100 papers, including best paper awards at ICML and ECML, and a Test of Time Award for his work, A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning, ICML 2008 with Ronan Collobert. He was part of the YouTube team that won a National Academy of Television Arts and Sciences Emmy Award for Technology and Engineering for Personalized Recommendation Engines for Video Discovery. He was listed as the 16th most influential machine learning scholar at AMiner and one of the top 50 authors in Computer Science in Science

    Host: Jon May and Mozhdeh Gheini

    More Info: https://nlg.isi.edu/nl-seminar/

    Webcast: https://usc.zoom.us/j/91906081447

    Location: Information Science Institute (ISI) - Virtual Only

    WebCast Link: https://usc.zoom.us/j/91906081447

    Audiences: Everyone Is Invited

    Posted By: Petet Zamar

    OutlookiCal
  • CS Colloquium: Abhinav Verma (University of Texas - Austin) - Neurosymbolic Reinforcement Learning

    Thu, Mar 04, 2021 @ 11:00 AM - 12:00 PM

    Computer Science

    Conferences, Lectures, & Seminars


    Speaker: Abhinav Verma, University of Texas - Austin

    Talk Title: Neurosymbolic Reinforcement Learning

    Series: CS Colloquium

    Abstract: Recent advances in Artificial Intelligence (AI) have been driven by deep neural networks. However, neural networks have certain well-known flaws: they are difficult to interpret and verify, have high variability, and lack domain awareness. These issues create a deficiency of trust and are hence a significant impediment to the deployment of AI in safety-critical applications. In this talk, I will present work that addresses these drawbacks via neurosymbolic learning in the reinforcement learning paradigm. Neurosymbolic agents combine experience based neural learning with partial symbolic knowledge expressed via programs in a Domain Specific Language (DSL). Using a DSL provides a principled mechanism to leverage high-level abstractionsfor machine learning models, and establishes a synergistic relationship between machine learning and program synthesis.

    To overcome the challenges of policy search in non-differentiable program space we introduce a meta-algorithm that is based on mirror descent, program synthesis, and imitation learning. This approach interleaves the use of synthesized symbolic programs to regularize neural learning with the imitation of gradient-based learning to improve the quality of synthesized programs. This perspective allows us to prove robust expected regret bounds and finite-sample guarantees for this algorithm. The theoretical results guaranteeing more reliable learning are accompanied by promising empirical results on complex tasks such as learning autonomous driving agents and generating interpretable programs for behavior annotation.

    This lecture satisfies requirements for CSCI 591: Research Colloquium

    Biography: Abhinav Verma is a PhD Candidate at the University of Texas at Austin, where he is advised by Swarat Chaudhuri. His research lies at the intersection of machine learning and formal methods, with a focus on building intelligent systems that are reliable, transparent, and secure. His work builds connections between the symbolic reasoning and inductive learning paradigms of artificial intelligence. He is currently supported by a JP Morgan AI Research PhD Fellowship.

    Host: Mukund Raghothaman / Bistra Dilkina

    Audiences: Everyone Is Invited

    Posted By: Assistant to CS chair

    OutlookiCal
  • Repeating EventUndergraduate Advisement Drop-in Hours

    Thu, Mar 04, 2021 @ 01:30 PM - 02:30 PM

    Computer Science

    Workshops & Infosessions


    Do you have a quick question? The CS advisement team will be available for drop-in live chat advisement for declared undergraduate students in our four majors during the spring semester on Tuesdays, Wednesdays, and Thursdays from 1:30pm to 2:30pm Pacific Time. Access the live chat on our website at: https://www.cs.usc.edu/chat/

    Location: Online

    Audiences: Undergrad

    View All Dates

    Posted By: USC Computer Science

    OutlookiCal
  • Career Conversations: How to Impress Employers

    Thu, Mar 04, 2021 @ 04:00 PM - 04:30 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    Will your skill set stand out to employers? Join our interactive Career Conversations with Viterbi Career Connections staff for an inside look at employer feedback for Viterbi students. During this session, learn practices to develop the key professionalism and communication skills employers want to see more of.

    To access this workshop:

    Log into Viterbi Career Gateway>> Events>>Workshops: https://shibboleth-viterbi-usc-csm.symplicity.com/sso/

    For more information about Labs & Open Forums, please visit viterbicareers.usc.edu/workshops.

    Location: Online

    Audiences: All Viterbi Students

    Posted By: RTH 218 Viterbi Career Connections

    OutlookiCal
  • Virtual Chat with Prof. Mike Gruntman from Department of Astronautical Engineering

    Thu, Mar 04, 2021 @ 05:00 PM - 06:00 PM

    Viterbi School of Engineering Masters Programs

    Student Activity


    Sure, they're distinguished and renowned experts in their fields, but Viterbi faculty were once students too. Learn valuable life lessons as they share their professional and personal stories! Together, VGSA and the VASE office presents the Virtual Chat with a Professor Series! These are meant to be informal conversations that you might have with a professor after class or in the hallways. Each session is open to all Viterbi graduate students. Join in to chat with Prof. Mike Gruntman!

    Audiences: Everyone Is Invited

    Posted By: Juli Legat

    OutlookiCal
  • Boeing Freshman Design Challenge

    Thu, Mar 04, 2021 @ 06:00 PM - 09:00 PM

    Viterbi School of Engineering Career Connections

    University Calendar


    Challenge Details: As the world's leading aerospace company, Boeing is the world's largest manufacturer of commercial airplanes and military aircraft. To continue this dominance, Boeing needs the young minds of tomorrow to provide innovative, new perspectives. For this reason, Boeing will be putting on a design challenge for the Freshmen class of USC. In this competition, teams of three or four freshmen will have two hours to work together and design a solution to a typical, real-world engineering problem.

    During this unique, resume-building experience, students will also have the opportunity to network with Boeing engineers and executives, who will be available to act as mentors and judges.

    Despite being virtual, food will be provided in the form of dining gift cards for participants. Prizes are provided to top participants!

    To RSVP log into Viterbi Career Gateway>> Events>> Information Sessions:
    https://shibboleth-viterbi-usc-csm.symplicity.com/sso

    Audiences: All Viterbi Students

    Posted By: RTH 218 Viterbi Career Connections

    OutlookiCal