0000000000463244
AUTHOR
Daiga Deksne
Priedēkļverbu sentika un funkcionalitāte latviešu valodā
Promocijas darba mērķis ir darbības vārda priedēkļu semantikas analīze un klasifikācija. Izmantojot plašu korpusa piemēru analīzi un radiālās kategorijas metodi, darbā izveidoti priedēkļu nozīmju modeļi, kas atspoguļo saistību starp priedēkļa prototipisko un atvasinātām nozīmēm. Vienā modelī atspoguļotas gan telpiskās, gan temporālās, gan kvantitatīvās nozīmes. Šāda pieeja latviešu valodniecībā līdz šim nav izmantota. Tā sniedz skaidrāku priekšstatu par nozīmju saistību un izplatību mūsdienu latviešu valodā. Nozīmju modeļus turpmāk var izmantot valodas apguvē un vārdnīcu veidošanā. Darbā pētīta arī prefiksoīdu un svešcilmes priedēkļu semantika, kā arī priedēkļu nozīmju sinonīmija un antonīm…
Predicting Next Dialogue Action in Emotionally Loaded Conversation
This paper reports on creating a neural network model for prediction of the next action in a dialogue considering conversation history, i.e. entities, context variables and emotion indicators marking emotionally loaded user utterances. Several experiments were performed to see how the information about emotions affects the accuracy of the model. For the purposes of these experiments, a dataset containing 206 dialogs in Latvian in the transport inquiry domain was created containing both neutral and emotionally loaded utterances. To see if the proposed next dialogue action prediction model architecture is suitable for other languages, the original Latvian utterances were translated into Engli…
Intent Detection System Based on Word Embeddings
Intent detection is one of the main tasks of a dialogue system. In this paper we present our intent detection system that is based on FastText word embeddings and neural network classifier. We find a significant improvement in the FastText sentence vectorization. The results show that our intent detection system provides state-of-the-art results on three English datasets outperforming many popular services.
Classification of prefix aiz- ‘away’ meanings: from Jānis Endzelīns approach to nowadays
The polysemic nature of prefixes in Latvian causes problems in prefix classification. Several authors in different time periods have proposed diverse prefix classification systems. In this research, three different classification systems of prefix aiz- ‘away’ are compared – the classification system created by Endzelīns (1971) in 1907, the classification system created by Soida in 1970 (printed in 2009), and the classification system proposed by Vulāne (2015). To ascertain which meanings are used nowadays the examples are drawn from the corpus. There are 11 prefixes in the Latvian language used in word-formation. In this research, prefix aiz- is chosen as it has a rich meaning system althou…