Logo: University of Southern California

Events Calendar



Select a calendar:



Filter May Events by Event Type:



Events for the 2nd week of May

  • Repeating EventSix Sigma Green Belt for Process Improvement

    Mon, May 07, 2018

    Executive Education

    Conferences, Lectures, & Seminars


    Abstract: Learn how to integrate principles of business, statistics, and engineering to achieve tangible results. Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality.

    More Info: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Audiences: Registered Attendees

    View All Dates

    Contact: Corporate & Professional Programs

    Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense - Marjan Ghazvininejad

    Mon, May 07, 2018 @ 10:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Candidate: Marjan Ghazvininejad

    Committee: Kevin Knight (chair), Morteza Dehghani, Jonathan May

    Title: Neural Creative Language Generation

    Time & place: Monday, May 7th, 10 am, GFS 204


    Abstract: Natural language generation (NLG) is a well-studied and still very challenging field in natural language processing. One of the less studied NLG tasks is the generation of creative texts such as jokes, puns, or poems. Multiple reasons contribute to the difficulty of research in this area. First, no immediate application exists for creative language generation. This has made the research on creative NLG extremely diverse, having different goals, assumptions, and constraints. Second, no quantitative measure exists for creative NLG tasks. Consequently, it is often difficult to tune the parameters of creative generation models and drive improvements to these systems. Lack of a quantitative metric and the absence of a well-defined immediate application makes comparing different methods and finding the state of the art an almost impossible task in this area. Finally, rule-based systems for creative language generation are not yet combined with deep learning methods. Rule-based systems are powerful in capturing human knowledge, but it is often too time-consuming to present all the required knowledge in rules. On the other hand, deep learning models can automatically extract knowledge from the data, but they often miss out some essential knowledge that can be easily captured in rule-based systems.
    In this work, we address these challenges for poetry generation, which is one of the main areas of creative language generation. We introduce password poems as a new application for poetry generation. These passwords are highly secure, and we show that they are easier to recall and preferable compared to passwords created by other methods that guarantee the same level of security. Furthermore, we combine finite-state machinery with deep learning models in a system for generating poems for any given topic. We introduce a quantitative metric for evaluating the generated poems and build the first interactive poetry generation system that enables users to revise system generated poems by adjusting style configuration settings like alliteration, concreteness and the sentiment of the poem. The system interface also allows users to rate the quality of the poem. We collect users' rating for poems with various style settings and use them to automatically tune the system style parameters. In order to improve the coherence of generated poems, we introduce a method to borrow ideas from existing human literature and build a poetry translation system. We study how poetry translation is different from translation of non-creative texts by measuring the language variation added during the translation process. We show that humans translate poems much more freely compared to general texts. Based on this observation, we build a machine translation system specifically for translating poetry which uses language variation in the translation process to generate rhythmic and rhyming translations.

    Location: 204

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense - Shuyang Gao

    Mon, May 07, 2018 @ 12:00 PM - 02:00 PM

    Thomas Lord Department of Computer Science

    University Calendar




    Title: Mutual Information Estimation and Its Applications to Machine Learning

    PhD Candidate: Shuyang Gao

    Date: May 7

    Time: 12pm

    Location: SOS B37


    Committee: Aram Galstyan, Greg Verg Steeg, Ilias Diakonikolas, Aiichiro Nakano, Roger Ghanem

    Abstract:
    Mutual information (MI) has been successfully applied to a wide variety of domains due to its remarkable property to measure dependencies between random variables. Despite its popularity and wide spread usage, a common unavoidable problem of mutual information is its estimation. In this thesis, we demonstrate that a popular class of nonparametric MI estimators based on k-nearest-neighbor graphs requires number of samples that scales exponentially with the true MI. Consequently, accurate estimation of MI between strongly dependent variables is possible only for prohibitively large sample size. This important yet overlooked shortcoming of the existing estimators is due to their implicit reliance on local uniformity of the underlying joint distribution. As a result, my thesis proposes two new estimation strategies to address this issue. The new estimators are robust to local non-uniformity, works well with limited data, and is able to capture relationship strengths over many orders of magnitude than the existing k-nearest-neighbor methods.

    Modern data mining and machine learning presents us with problems which may contain thousands of variables and we need to identify only the most promising strong relationships. Therefore, caution must be taken when applying mutual information to such real-world scenarios. By taking these concerns into account, my thesis then demonstrates the practical applicability of mutual information on several tasks, and our contributions include
    i) an information-theoretic framework for measuring stylistic coordination in dialogues. The proposed measure has a simple predictive interpretation and can account for various confounding factors through proper conditioning ii) an new algorithm for mutual information-based feature selection in supervised learning setting iii) an information-theoretic framework for learning disentangled and interpretable representations in unsupervised setting using deep neural networks. For the latter two tasks, we propose to use a variational lower bound for efficient estimation and optimization of mutual information. And for the last task, we have also made a substantial connection of the learning objective with variational auto-encoders (VAE).

    Location: Social Sciences Building (SOS) - B37

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense - Kuan Liu

    Mon, May 07, 2018 @ 01:00 PM - 03:00 PM

    Thomas Lord Department of Computer Science

    University Calendar



    PhD Candidate: Kuan Liu

    Title: Scalable machine learning algorithms for implicit feedback based recommendation

    Committee: Prem Natarajan, Kevin Knight, Shri Narayanan (outside member)


    SAL 322
    May 7
    1-3pm


    Abstract:

    Whether in e-commerce, social networks, online music and TV, and many other modern online services, item recommendation stands out to be one of the most important algorithmic components. It recommends items to users that are useful and relevant. It makes huge economic values and is an important information filtering tool.

    The primary goal of this thesis research is to provide machine learning solutions to item recommendation in large scale. The ever-increasing data volume and rich data formats have created a big gap between the requirements of modern recommender systems and our algorithm ability to handle large scale tasks. We work towards efficient personalized ranking algorithms to handle large data volume and advance content-based approaches to incorporate rich side information.

    The thesis work mainly focuses on the following aspects towards this goal: (1) Novel ranking algorithms to deal with large itemsets (2) Deep learning methods to model sequential properties of user feedback (3) To incorporate heterogeneous attributes (4) To fuse signals from multiple modalities. In this talk, I will provide a brief overview of item recommendation history and our contributions. I will discuss our recent work on batch-based ranking algorithms for recommendation from large itemsets and our new methods to fuse signals from multiple modalities.

    Location: Henry Salvatori Computer Science Center (SAL) - 322

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Repeating EventSix Sigma Green Belt for Process Improvement

    Tue, May 08, 2018

    Executive Education

    Conferences, Lectures, & Seminars


    Abstract: Learn how to integrate principles of business, statistics, and engineering to achieve tangible results. Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality.

    More Info: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Audiences: Registered Attendees

    View All Dates

    Contact: Corporate & Professional Programs

    Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense - Xing Shi

    Tue, May 08, 2018 @ 10:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Candidate: Xing Shi

    Date: May 8, 10am at SAL 322

    Committee: Kevin Knight (chair), Jonathan May and Shri Narayanan

    Abstract:

    Recurrent neural networks (RNN) have been successfully applied to various Natural Language Processing tasks, including language modeling, machine translation, text generation, etc. However, several obstacles still stand in the way: First, due to the RNN's distributional nature, few interpretations of its internal mechanism are obtained, and it remains a black box. Second, because of the large vocabulary sets involved, the text generation is very time-consuming. Third, there is no flexible way to constrain the generation of the sequence model with external knowledge. Last, huge training data must be collected to guarantee the performance of these neural models, whereas annotated data such as parallel data used in machine translation are expensive to obtain. This work aims to address the four challenges mentioned above.

    To further understand the internal mechanism of the RNN, we choose neural machine translation (NMT) systems as a testbed. We first investigate how NMT outputs target strings of appropriate lengths, locating a collection of hidden units that learns to explicitly implement this functionality. Then we investigate whether NMT systems learn source language syntax as a by-product of training on string pairs. We find that both local and global syntactic information about source sentences is captured by the encoder. Different types of syntax are stored in different layers, with different concentration degrees.

    To speed up text generation, we propose two novel GPU-based algorithms: 1) Utilize the source/target words alignment information to shrink the target side run-time vocabulary; 2) Apply locality sensitive hashing to find nearest word embeddings. Both methods lead to a 2-3x speedup on four translation tasks without hurting machine translation accuracy as measured by BLEU. Furthermore, we integrate a finite state acceptor into the neural sequence model during generation, providing a flexible way to constrain the output, and we successfully apply this to poem generation, in order to control the meter and rhyme.

    To improve NMT performance on low-resource language pairs, we re-examine multiple technologies that are used in high resource language NMT and other NLP tasks, explore their variations and result in a strong NMT system for low resource languages. Experiments on Uygher-English shows a 10+ BLEU score improvement over the vanilla NMT system.

    Location: Henry Salvatori Computer Science Center (SAL) - 322

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense- Soravit (Beer) Changpinyo

    Tue, May 08, 2018 @ 12:00 PM - 02:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Candidate: Soravit (Beer) Changpinyo
    Committee: Fei Sha (chair), Kevin Knight, C.-C. Jay Kuo (outside member)

    Title: Modeling, Learning, and Leveraging Similarity
    Time & Place: Tuesday, May 8th, 12-2pm, SAL 213
    Abstract:
    Measuring similarity between any two entities is an essential component in most machine learning tasks. In this defense, I will describe my research work that provides a set of techniques revolving around the notion of similarity.
    The first part involves "modeling and learning" similarity. We introduce Similarity Component Analysis (SCA), a Bayesian network for modeling instance-level similarity that does not observe the triangle inequality. Such a modeling choice avoids the transitivity bias in most existing similarity models, making SCA intuitively more aligned with the human perception of similarity.
    The second part involves "learning and leveraging" similarity for effective learning with limited data, with applications in computer vision and natural language processing. We first leverage incomplete and noisy similarity graphs in different modalities to aid the learning of object recognition models. In particular, we propose two novel zero-shot learning algorithms that utilize class-level semantic similarities as a building block, establishing state-of-the-art performance on the large-scale benchmark with more than 20,000 categories. As for natural language processing, we employ multi-task learning (MTL) to leverage unknown similarities between sequence tagging tasks. This study leads to insights regarding the benefit of going to beyond pairwise MTL, task selection strategies, as well as the nature of the relationships between those tasks.

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense - Sayan Ghosh

    Tue, May 08, 2018 @ 02:00 PM - 04:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Title : Multimodal Representation Learning of Affective Behavior

    PhD Candidate: Sayan Ghosh

    Date : 8th May , 2 PM PST
    Venue: PHE 223
    Committee : Prof. Stefan Scherer (Chair), Prof. Louis-Philippe Morency, Prof. Kevin Knight, Prof. Panayiotis Georgiou (EE)

    Abstract:
    With the ever increasing abundance of multimedia data available on the Internet and crowd-sourced datasets/repositories, there has been a renewed interest in machine learning approaches for solving real-life perception problems. However, such techniques have only recently made inroads into research problems relevant to the study of human emotion and behavior understanding. The primary research challenges addressed in this defense talk pertain to unimodal and multimodal representation learning, and the fusion of emotional and non-verbal cues for language modeling . There are three primary contributions of this dissertation -
    (1) Unimodal Representation Learning: In the visual modality a novel multi-label CNN (Convolutional Neural Network) is proposed for learning AU (Action Unit) occurrences in facial images. The multi-label CNN learns a joint representation for AU occurrences, obtaining competitive detection results; and is also robust across different datasets. For the acoustic modality, denoising autoencoders and RNNs (Recurrent Neural Networks) are trained on temporal frames from speech spectrograms, and it is observed that representation learning from the glottal flow signal (the component of the speech signal with vocal tract influence removed) can be applied to speech emotion recognition.
    (2) Multimodal Representation Learning: An importance-based multimodal autoencoder (IMA) model is introduced which can learn joint multimodal representations as well as importance weights for each modality. The IMA model achieves performance improvement relative to baseline approaches for the tasks of digit recognition and emotion understanding from spoken utterances.
    (3) Non-verbal and Affective Language Models: This dissertation studies deep multimodal fusion in the context of neural language modeling by introducing two novel approaches - Affect-LM and Speech-LM. These models obtain perplexity reductions over a baseline language model by integrating verbal affective and non-verbal acoustic cues with the linguistic context for predicting the next word. Affect-LM also generates text in different emotions at various levels of intensity. The generated sentences are emotionally expressive while maintaining grammatical correctness as evaluated through a crowd-sourced perception study.

    Location: Charles Lee Powell Hall (PHE) - 223

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • INCOSE-LA Speaker Meeting

    INCOSE-LA Speaker Meeting

    Tue, May 08, 2018 @ 05:15 PM - 07:30 PM

    Systems Architecting and Engineering, USC Viterbi School of Engineering

    Conferences, Lectures, & Seminars


    Speaker: Kay Das, INCOSE - Los Angeles

    Talk Title: The Connected Vehicle Revolution - Continued

    Series: INCOSE-LA Speaker Series

    Abstract: The second installment of our light-hearted but critical look at the Connected Vehicle revolution. There is currently much ongoing activity in the research and design of systems to enhance the safety of vehicular traffic on roads and highways. These include vehicle-to-vehicle based and vehicle-to-infrastructure based electronics systems with extension to personal devices. These systems need to work collaboratively in an intelligent and reconfigurable network environment characterized by multiple localized and dynamically changing motion control loops which include each individual vehicle driver (and pedestrian). Systems will comprise a mix of existing and new technologies such as laser, imaging, computer vision, radar, cellular, WiFi, GPS, millimetric Waves, and others. System complexity is very high to deliver and sustain the required levels of reliability. A range of products and systems will compete for market entry from diverse developers and nations. Compliance with a safety culture within product development, such as directed by the ISO 26262 cocoon, is desirable. Safety needs to be regarded as an integral and critical element in system, software, hardware, and device and sensor design. A significant challenge also exists in validating prototypes and final systems productized for market entry. The cost of failure is high as human life is in the loop. This presentation reviews some of the challenges and offers some directions for this burgeoning industry propelled by developments ranging from Shannons Law and Moores Law to the evolving Internet of Things and 5G cellular communications. Management of systems research and development with frugality, without over-design, and with a holistic approach on a scale probably never demanded before, is required.

    RSVP: Required, see the event link below.

    WHERE: Rockwell Collins - Irvine
    1733 Alton Pkwy,
    Irvine, CA 92606
    Host: Andrew Murrell
    Phone: 714-929-3503

    When you arrive please wait in the Rockwell Collins Lobby in Building 18 (A Rockwell Collins sign will be on the building) and check in with Security, you will need to present identification and a visitor badge will be issued. A Rockwell Employee will then escort you to the Conference room.

    COST: INCOSE Members: FREE. Non-members: $10 (refreshments provided)

    SCHEDULE:
    5:15-5:30 Sign-in and Registration
    5:30-6:00 Networking and Refreshments
    6:10-6:20 Introduction
    6:20-6:30 WG Presentation (TBD)
    6:30-7:30 Guest Speaker Presentation

    Biography: Kay Das was GPS Program Manager and Technical Director at LinQuest Corporation in Los Angeles from 2007 to 2013 where he additionally led new business development thrusts in the commercial and automotive safety markets. He has previously held responsibilities as R&D Director for STMicroelectronics Asia Pacific region. He is a winner of a Singapore Government National Award for The Initiation and Expansion of High-value R&D and Promotion of Partnerships. He has built and led teams in different parts of the world and managed the development of diverse silicon-based signal processing systems over 40 years in industry. His current pursuits are the application of communication (such as 5G-DSRC) and location technologies (such as GPS-GNSS) to the Connected Vehicle revolution. He holds an MS in Electronics Systems from the Cranfield Institute of Technology, UK. His pursuits in retirement other than Connected Vehicle include amateur astronomy, Internet radio, and he is a professional musician. He is an IEEE Life Member and a member of several societies.

    Host: International Council on Systems Engineering (INCOSE)

    More Info: http://events.r20.constantcontact.com/register/event?llr=l4ihvgeab&oeidk=a07ef7zwisr1ddb5ba8

    Location: Rockwell Collins - Irvine

    Audiences: Everyone Is Invited

    Contact: Deborah A. Cannon

    Event Link: http://events.r20.constantcontact.com/register/event?llr=l4ihvgeab&oeidk=a07ef7zwisr1ddb5ba8

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Repeating EventSix Sigma Green Belt for Process Improvement

    Wed, May 09, 2018

    Executive Education

    Conferences, Lectures, & Seminars


    Abstract: Learn how to integrate principles of business, statistics, and engineering to achieve tangible results. Master the use of Six Sigma to quantify the critical quality issues in your company. Once the issues have been quantified, statistics can be applied to provide probabilities of success and failure. Six Sigma methods increase productivity and enhance quality.

    More Info: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Audiences: Registered Attendees

    View All Dates

    Contact: Corporate & Professional Programs

    Event Link: https://viterbiexeced.usc.edu/engineering-program-areas/six-sigma-lean-certification/six-sigma-green-belt-process-improvement/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense- Haifeng Xu

    Wed, May 09, 2018 @ 10:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Title: Information as A Double-Edged Sword in Strategic Interactions

    PhD Candidate: Haifeng Xu

    Committee:
    Shaddin Dughmi (Chair), Milind Tambe (Chair), David Kempe, Detlof von Winterfeldt, Vincent Conitzer, Odilon Camara.

    Location & Time: SSL 150, 10 - 12 pm May 9th.

    Abstract:

    Strategic interactions among self-interested agents (a.k.a., games) are ubiquitous, ranging from economic activity in daily life and the Internet to defender-adversary interactions in national security. A key variable influencing agents' strategic decision making is the information they have available about their environment as well as the preferences and actions of others. In this talk, I will describe my work on computational questions pertaining to the role of information in games. In particular, I will illustrate the double-edged role of information through two threads of my research: (1) how to utilize information to one's own advantage in strategic interactions; (2) how to mitigate losses resulting from information leakage to an adversary. In each part, I will demonstrate how the study of fundamental theoretical questions sheds light on executable solutions to real-world problems in security applications including, e.g., delivered software to the Federal Air Marshal Service for improving the scheduling of US federal air marshals.

    Location: 150

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense- Sean Mason

    Wed, May 09, 2018 @ 10:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    University Calendar



    Title: Optimization Based Whole-Body Control and Reactive Planning for a Torque Controlled Humanoid Robot

    PhD Candidate: Sean Mason

    Date and Time: Wednesday May 9, 2018 at 10:00 AM in RTH 406

    Committee: Stefan Schaal (Chair), Gaurav Sukatme, James Finley, Ludovic Righetti

    Abstract:
    Humanoid robots are expected to both locomote and interact with objects within unstructured environments. As robot hardware technologies have advanced, high-bandwidth, torque-controlled robots have become more widely-available as research platforms. In this work, I explore optimization-based methods for planning and control of a humanoid robot. I focus on the importance of controlling contact interactions with the environment for the tasks of balancing and walking of a bipedal system. This work is driven by and centered on the challenge of real robot implementations, and thus addresses the questions that come along with designing control algorithms for real systems. I will present lightweight control algorithms for whole-body balance, a model-predictive control approach to walking while using hands, and show extensive experiments on a humanoid robot.

    Location: Ronald Tutor Hall of Engineering (RTH) - 406

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Defense - Kyriakos Zarifis

    Wed, May 09, 2018 @ 01:00 PM - 03:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Title: Making Web Transfers More Efficient

    PhD Candidate: Kyriakos Zarifis

    Date: 05-09-18
    1pm
    SAL 322

    Committee:
    Ethan Katz-Bassett (Chair)
    Ramesh Govindan
    Konstantinos Psounis (Outside)

    Abstract:
    Delays in web applications have been repeatedly shown to negatively impact business revenues. In this dissertation we perform studies related to Web transfer delays specific to propagation delay due to inflated paths, and delays in transferring data between servers and clients due to inefficient use of the communication channels.
    Previous research has shown that the shortest path between a client and a server is not always selected, due to routing protocol policy-based decisions. We develop a methodology identify root causes of path inflation, specifically focusing on mobile traffic directed to Google servers, in order to understand the evolution of the infrastructure of mobile carrier networks and how it can affect user experience.
    Once a connection has been established, information is exchanged between the two hosts according to rules defined by HTTP, the application layer protocol used for today's Web transfers. In this work we develop a model of the new version of HTTP/2 and pass through it a large dataset of HTTP/1 traces, in order to understand the performance implications of deploying the new version of the protocol in the wild. Our study exposes several opportunities for improvements, specifically using a new feature that allows a server to send to the client an object without the client requesting it. Generalizing from that observation, we design, develop and evaluate a system that allows CDNs to utilize idle network time around page downloads to send to the client content that the client is expected to request in the current or next page navigation. We show that if implemented correctly, speculative content prepositioning on the client can achieve a performance improvement comparable to having a page loaded on the client cache.

    Location: 322

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Viterbi School of Engineering PhD Hooding and Awards Ceremony

    Thu, May 10, 2018 @ 08:30 AM - 11:00 AM

    Viterbi School of Engineering Doctoral Programs

    Receptions & Special Events


    The Viterbi PhD Hooding and Awards Ceremony will take place on Thursday, May 10, 2018, from 8:30-11:00am in Bovard Auditorium. Tickets are required.

    The ceremony will be followed by a reception in Associates Park.

    Location: George Finley Bovard Administration Building (ADM) -

    Audiences: Everyone Is Invited

    Contact: Jennifer Gerson

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • NL Seminar Towards Flexible but Controllable Language Generation

    Fri, May 11, 2018 @ 03:00 PM - 04:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Yulia Tsvetkov , CMU

    Talk Title: Towards Flexible but Controllable Language Generation

    Series: Natural Language Seminar

    Abstract: To enable naturalistic, context aware language generation, the underlying models must be flexible but controllable. They must be flexible enough to account for the rich linguistic diversity of data that the model generates and conditions on. On the other hand, generation must be controlled, to lexicalize the same meaning differently, depending upon the social and the situational context. I will present model based approaches to multilingual language modeling and open vocabulary machine translation, aiming at making language generation more flexible by relaxing the unreasonable but prevalent in the literature assumption that a models vocabulary is constrained to a particular set of most frequent words in a particular language. Then, I will present an approach to controllable text generation that modulates social variables in generated text. I will conclude with an overview of ongoing research projects.

    Biography: Yulia Tsvetkov is an assistant professor in the Language Technologies Institute at Carnegie Mellon University. Her research interests lie at or near the intersection of natural language processing, machine learning, linguistics, and social science. Her current research projects focus on multilinguality e.g., open vocabulary machine translation, polyglot models, entrainment in code switching, controllable text generation, automated negotiation, and NLP for social good e.g., identification of microaggressions and dehumanization in online interactions, identification of misinformation and agenda setting in news, predicting scientific misconduct. Prior to joining LTI, Yulia was a postdoc in the department of Computer Science at Stanford University she received her PhD from Carnegie Mellon University.

    Host: Nanyun Peng

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

    Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey

    Audiences: Everyone Is Invited

    Contact: Peter Zamar

    Event Link: http://nlg.isi.edu/nl-seminar/

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File