AI for Language Technologies

Work Package 5

AI for Language Technologies

– LANG

Man in libarary speaking on his mobil

The purpose for this work package is

  1. To build robust natural language processing for Scandinavian languages
  2. To provide conversational search and recommendations in natural language
  3. To develop natural language summarization of content, user preferences, and recommendations

 

Building Scandinavian language models requires the compilation of large-scale reusable language resources, including general-purpose corpora from public sources (e.g., news and social media) as well as industry- and domain-specific text collections. We will address the scarcity of the latter by pre-training on the former and developing transfer learning methods. These large-scale language models will then be utilized in real-life scenarios by formulating a number of specific summarization, explanation, and conversational tasks based on our partners’ use-cases. WP5 will develop appropriate evaluation methodology with user-oriented evaluation measures and objectives. It will thus contribute to providing measurable quantification of the amount of domain-specific training material needed in order to provide a language service that is of sufficiently high quality.


People

People

person-portlet

Projects

Projects

Projects

Short description: Based on a very large corpus consisting of newspaper articles from most Norwegian newspapers, NorwAI will create the largest Norwegian language model built so far, enabling new opportunities within areas as chatbots and text summarization.

Time perspective: 2020-

Involved partners: 

Logo Retriever

Logo Schibsted

Logo NR

Logo UiO

Logo DNB

Logo UiS

Stories

Stories

New Language Models in NorwAI

New Language Models in NorwAI

Photo. Jon Atle Gulla

The NorwAI center is determined to provide new Norwegian language models that are significantly larger and better than what is available to-day and can easily be employed in advanced Norwegian NLP applications for industrial use, says center director professor Jon Atle Gulla.

Read more