Life-Long Learning for Spoken Language Systems Workshop
LifeLong@ASRU 2019
- URL: https://sites.google.com/view/life-long-learning-asru19/
- Event Date: 2019-12-14 ~ 2019-12-14
- Submission Date: 2019-10-18
# Overview
Machine learning in speech often strongly relies on the large data annotated data-sets to train the models. However, data collection and manual annotation is a time-consuming, expensive process that requires to be bootstrapped with a good enough model. This slows down the development of new features and products.
The literature on bootstrapping ML systems often overlook 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).
In addition, several methods, like active, transfer, semi-supervised learning or data augmentation are designed for small data sets but would not scale to data sets with millions of annotated data and billions of the unannotated data. To address this issue, efforts for real-world applications should adapt those methods to target only features (or classes) recently introduced. For example, machine reading comprehension models do very well on 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.
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.
Machine learning in speech often strongly relies on the large data annotated data-sets to train the models. However, data collection and manual annotation is a time-consuming, expensive process that requires to be bootstrapped with a good enough model. This slows down the development of new features and products.
The literature on bootstrapping ML systems often overlook 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).
In addition, several methods, like active, transfer, semi-supervised learning or data augmentation are designed for small data sets but would not scale to data sets with millions of annotated data and billions of the unannotated data. To address this issue, efforts for real-world applications should adapt those methods to target only features (or classes) recently introduced. For example, machine reading comprehension models do very well on 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.
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.
Journal Promotion
|
| Acta Koreana (Acta Koreana) |
|
| Acta Via Serica (AVS) |
|
| Computers and Concrete (CAC) |
|
| Journal of Information Processing Systems (JIPS) |
|
| Journal of Internet Computing and Services (KSII - JICS) |
|
| Journal of Smart Tourism (Smart Tourism) |
|
| Membrane and Water Treatment (MWT) |
|
| Wind and Structures, An International Journal (Wind and Structures) |
MANUSCRIPTLINK © 2015 -
