Life-Long Learning for Spoken Language Systems

Description

This is the webpage of the Life Long Learning for Spoken Language Systems Workshop colocated with ASRU 2019, in Singapore.

The workshop will bring together experts in spoken language systems whose research focuses on solving problems related to continual improvement of speech processing systems such as conversational AI. Specifically, it will provide attendees with an overview of existing approaches from various disciplines including but not limited to active learning, few-shot learning, data augmentation, and enable them to distill principles that can be more generally applicable. It will also discuss the main challenges arising in bringing speech technology systems to masses and continuous improvement of such systems. The target audience consists of researchers and practitioners in related areas.

For updated information, please visit this website.

Important Dates

  • Call For Papers: September 1, 2019
  • Deadline for submission: October 28, 2019
  • Notification of acceptance: November 8, 2019
  • Deadline for camera-ready version: November 15, 2019
  • Workshop Date: December 14, 2019

Invited Speakers

Call For Papers

Machine learning for speech and language understanding tasks often strongly relies on large annotated data-sets to train the models. However, data collection and manual annotation is a time-consuming, expensive process often requiring a variety of bootstrapping methods to produce models that are “good enough”. This slows down the development of new features and products.

The literature on bootstrapping ML systems often overlooks the constraints of real-world applications related to:

  • annotation processes (examples are often annotated by batches instead of one by one);
  • privacy (transfer learning from one language to another often requires to move data from one continent to another, which violates privacy policies);
  • training times and resources;
  • continual learning (introducing new classes but also merging or removing old ones).

The ability to efficiently move real-world systems to new domains and languages, or to adapt to changing conditions over time also often requires a complex mixture of techniques including active learning, transfer learning, continuous on-line learning, semi-supervised learning, and data augmentation as the models used by existing systems rarely generalize well to new circumstances. For example, current machine reading comprehension models do very well answering general, factoid style questions, but perform poorly on new specialized domains such as legal documents, operational manuals, financial policies, etc. Thus, domain transfer (especially from limited annotated data or using only unsupervised techniques) is needed to make the technology work for new scenarios. To address such issues, efforts for real-world applications need improved methods for targeting new use cases, features or classes. The approach also needs to be scalable to learn from both small limited-data sets at the beginning of a system’s life-cycle to larger data sets with millions of annotated data and/or billions of unannotated data as deployed systems expand to larger user bases and use cases.

In this workshop, we aim to cover challenges in a lifelong process where new users or functionalities are added, and existing functionalities are modified. We believe the challenge is prevalent in research from both academia and industry.

Topics of Interest

  • Semi-supervised learning
  • Active learning
  • Unsupervised learning
  • Incremental learning
  • Domain adaptation
  • Data generation/augmentation
  • Few shot learning
  • Zero shot learning

Submission Guidelines

Please submit your paper using EasyChair.

Format: Submissions must be in PDF format, anonymized for review, written in English and follow the ASRU 2019 formatting requirements, available here. We advise you use the LaTeX template files provided by ASRU 2019.

Length: Submissions consist of up to eight pages of content. There is no limit on the number of pages for references. There is no extra space for appendices. There is no explicit short paper track, but you should feel free to submit your paper regardless of its length. Reviewers will be instructed not to penalize papers for being too short.

Dual Submission: Authors can make submissions that are also under review at other venues, provided it does not violate the policy at those venues.We do NOT require submissions to follow an anonymity period.

Presentation Format: We anticipate most papers will be presented as posters, with only a few selected for oral presentation.

Organizing Committee

Program Committee

  • Jan Niehues, Maastricht University
  • Elizabeth Salesky, CMU
  • Christian Federmann, Microsoft
  • Abhyuday Jagannatha, UMass Amherst
  • Beat Gfeller, Google Research
  • Hassan Rom, Google Research
  • Matthias Sperber, Apple
  • John Lalor, University of Notre Dame
  • Ankur Gandhe, Alexa Speech
  • Teresa Herrmann, Echobot Media Technologies GmbH/Karlsruhe Institute of Technology
  • Varun Nagaraja, Alexa Speech
  • Nick Ruiz, Interactions LLC
  • Krishna C. Puvvada, Alexa Speech
  • Jervis Pinto, Electronic Arts

Contact

Organizers can be reached at life-long-learning-asru19@googlegroups.com