Towards SamiTalk: A Sami-Speaking Robot Linked to Sami Wikipedia

Wilcock, Graham; Laxström, Niklas; Leinonen, Juho; Smit, Peter; Kurimo, Mikko; Jokinen, Kristiina

doi:10.1007/978-981-10-2585-3_28

Cited by 6 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DigiSami focuses especially on North Sámi, and sets to collect data, provide tools, and develop technology to enable North Sámi speech-based applications to be developed (Jokinen and Wilcock, 2014a). Moreover, the project aims to encourage community effort for online content creation, and for this, Wikipedia-based applications are supported, such as WikiTalk (Jokinen and Wilcock, 2014b;Wilcock et al, 2016). This is a robot-application which allows the user to interact with a robot concerning information in the Wikipedia articles.…”

Section: Related Work On North Sámimentioning

confidence: 99%

Low-Resource Active Learning of Morphological Segmentation

Grönroos

Hiovain

Smit

et al. 2016

NEJLT

Self Cite

View full text Add to dashboard Cite

Many Uralic languages have a rich morphological structure, but lack morphological analysis tools needed for efficient language processing. While creating a high-quality morphological analyzer requires a significant amount of expert labor, data-driven approaches may provide sufficient quality for many applications. We study how to create a statistical model for morphological segmentation with a large unannotated corpus and a small amount of annotated word forms selected using an active learning approach. We apply the procedure to two Finno-Ugric languages: Finnish and North Sámi. The semi-supervised Morfessor FlatCat method is used for statistical learning. For Finnish, we set up a simulated scenario to test various active learning query strategies. The best performance is provided by a coverage-based strategy on word initial and final substrings. For North Sámi we collect a set of humanannotated data. With 300 words annotated with our active learning setup, we see a relative improvement in morph boundary F 1 -score of 19% compared to unsupervised learning and 7.8% compared to random selection.

show abstract

Section: Related Work On North Sámimentioning

confidence: 99%

Low-Resource Active Learning of Morphological Segmentation

Grönroos

Hiovain

Smit

et al. 2016

NEJLT

Self Cite

View full text Add to dashboard Cite

show abstract

“…[109] performs a very similar task, being able to interact with several people, a very common issue in places with people as a laboratory or a museum. [110] performs a similar task with the robot NAO which can speak english and sami language. Emotions Task and the TTS module will be explained in sections 5.4 and 5.2 respectively.…”

Section: The Speaking Systemmentioning

confidence: 99%