Applied Language Technology
Applied language technology will be key for making the most of AI and enables tasks as wide ranging as using voice assistants at home to a reliable automatization of certain social services. To accelerate innovation, development of applications, and implementation in this area, Applied Language Technology therefore constitutes one of AI Sweden’s strategic programs.
What is Applied Language Technology?
Applied Language Technology is a collective term for the applied aspects of how computer programs or electronic devices can analyze, produce, modify or respond to human texts and speech. Natural Language Processing (NLP) is a core element of this area. NLP algorithms, or language models, learn from language data, enabling machine understanding and machine representation of natural (human) language. Using NLP, applications and tools can be used to identify patterns and provide insights hidden in large amounts of language data, too vast for humans to process. Based on patterns and insights, unstructured data can be turned into actionable information, allowing us to make data-driven and well-informed decisions.
In order for Sweden to benefit from the rapid development in the applied language technology area, language models need to be trained on datasets for Swedish and minority languages spoken in Sweden.
Projects and Platforms
Presentation: Annotated Job Ads with Swedish Language Models
'Annotated Job Ads with Swedish Language Models'
Felix Stollenwerk, Arbetsförmedlingen/Swedish Public Employment Service
Swedish NLP webinar 19 November 2020
Presentation: Semantic Sentence Embeddings with Contrastive Tension
'Semantic Sentence Embeddings with Contrastive Tension with Contrastive Tension'
Fredrik Carlsson, RISE Research Institutes of Sweden
Swedish NLP webinar 5 November 2020
Presentation: Data Readiness for Natural Language Processing
'Data Readiness for Natural Language Processing'
Fredrik Olsson, RISE Research Institutes of Sweden
Swedish NLP webinar 22 October 2020
Report: First and last names for dialogue on Swedish NER data
Swedish Language Data Lab: During autumn 2019, Talkamatic conducted their analysis of the annotation and applicability in dialogue settings of the Swedish NER model, developed by Recorded Future. Their initial results were presented at the first reference group meeting in December 2019, and are described in this report.
Report: Data and AI are transforming news media
Presentation: NLP and disinformation: Detection of computer-generated text
'Presentation: NLP and disinformation: Detection of computer-generated text'
Fredrik Johansson, FOI
Swedish NLP webinar 3 March 2021