Develop NLP Habits of Mind: Expand the boundaries of localization with AI
Instructor: Dr. Peng Wang
Tuesday, March 15 – 12:00pm – 2:30pm CT
Duration: 2 Hours, 30 minutes
“Natural language processing is an important application area of artificial intelligence. Through parsing, tagging and analyzing naturally occurring texts or speeches, computer programs can achieve a certain level of language understanding like humans, including extracting the meaning or intent behind language. NLP is fueled by data, powered by a range of computational techniques, and driven by human purposes.” (Peng Wang 2021)
A few examples of NLP tasks in localization: machine translation, translation-related text analysis, text summarization, text classification, multilingual information retrieval and speech recognition.
Presented In: English
To harness the power of AI, the key to success is more humans than data, as humans create data but not vice versa. Stakeholders need to understand NLP as a new dimension of thinking that changes the way of how a localization process is organized. With this mindset, your NLP tools will be able to help you achieve your business goals in your own way.
This session helps localizers develop NLP habits of mind. It will demystify threshold concepts and introduce use cases of processing human-touched data. Participants will get hands-on experience in an AI simulation game to understand and develop their own thoughts on NLP.
What to do when translation becomes a side product of localization?
From a NLP perspective, what a localization process can generate is far more than translation itself. When translation is not the only option that accounts for most part of human work, how do you use your manpower? Time to give it some thought – the earlier, the better.
How to maximize the value of data for humans?
Data can serve both humans and machines. From an engineer’s perspective, language data is mostly fed to computer programs to train the model. On the other hand, from a social perspective, data can augment humans’ perception and help them learn. NLP thinking can help maximize the value of data for humans.
Participants will learn:
- Fundamental NLP AI knowledge and methodologies
- How to get insights from data and metadata
- How to add cultural intelligence to data
- How to use NLP to cut down the cost without compromising on quality
- How to effectively manage your man power in an AI driven localization process
The class aims to empower you with basic NLP tools and methodologies. By developing NLP mindsets, you will be able to incorporate AI into your existing business strategic plans and/or personal career development. This class has no specific prerequisites in terms of technical experience and previous knowledge on NLP AI.
Job titles may include:
- Project Managers tasked with implementing a NLP AI solution
- Vendors who want to leverage NLP AI to meet their clients’ needs
- Buyers who want to implement NLP AI
- Decision-makers who have to understand NLP AI but don’t want to become technical experts
- IT professionals involved in NLP implementation
- Content Managers responsible for global content
Part I: Demystify threshold concepts: NLP, AI and ML
Part II: Human-touched data: types and annotation
Part II: NLP tasks and use cases in localization
Part IV: AI simulation game
Participants will have time to participate in an AI simulation game to develop their thoughts and ideas on NLP. The game will be conducted and reviewed from both the buyers’ and the suppliers’ perspectives. In addition, all participants will learn how to clean and annotate data so that they can customize their own models based on specific business goals.
About Your Trainer
Dr. Peng Wang has taught, researched and practiced translation and localization on three continents. She is the convener for EDUinLOC, the chair of the automation/AI track for LocWorld conferences and a part-time professor at the University of Ottawa. Previously, she was the CAT Tools Coordinator at the University of Maryland.
Dr. Wang has rich research experience on NLP AI, having worked as a linguistic researcher at the Corpus Research Lab at Northern Arizona University, a domain expert for data mining projects at the University of Maryland and an honorary research fellow on automatic discourse analysis tools at the University of Liverpool. Her current research and practice focus on human learning vs. machine learning, machine translation, terminology and multilingual corpus analysis.
Dr. Wang has published about 30 articles and two books. One of her most recent publications is entitled On The Role Of Machine Learning In A Human Learning Process, in which she investigated word distribution in vector space trained on different corpora and how human learners gather insights from machine learning results.
Check out Dr. Wang’s Machine Translation Master Class.
Some might wonder how the Ready Set Go: Think NLP is different from another class I am offering in January 2022: Machine Translation Master Class. If so, please check out the following table to compare their features:
|Machine Translation Master Class||Think NLP RSG class|
|In common||Both classes are on technology, but prioritize humans. They approach translation and localization from the perspective of a linguist, a project manager and other domain expert, as opposed to a technical expert such as a computer programmer, both of whom are main drivers leveraging AI to magnify and scale human knowledge of translation.|
|Differences||● It focuses on machine translation as well as other tasks associated with MT implementation.
● It includes both the conventional CAT tool environment and innovations MT can bring about.
● It emphasizes humans’ role in MT quality evaluation, estimation and overall quality control.
|● It does not prioritize any particular application, but tells the story of neural network language models.
● It includes multiple NLP tasks that have been or can be applied in a localization process.
● It depicts the role of localizers in data collection, annotation, management and application.
|Key Takeaways||● Knowledge of multiple MT paradigms
● A perception of what innovations MT could bring to a CAT tool environment
● An understanding of humans’ role in MT quality evaluation, estimation and overall quality control
● An understanding of how to coordinate between MT and its supporting techniques
|● Fundamental NLP AI knowledge and methodologies
● An understanding of how to get insights from data and metadata as well as a localizer’s role in this process
● A NLP mindset to help you think proactively to leverage NLP AI in your business
● A perception of how to effectively motivate and manage your man power in an AI driven localization process
Terms and Conditions