Essays about: "low resource language"
Showing result 1 - 5 of 47 essays containing the words low resource language.
-
1. How negation influences word order in languages : Automatic classification of word order preference in positive and negative transitive clauses
University essay from Uppsala universitet/Institutionen för lingvistik och filologiAbstract : In this work, we explore the possibility of using word alignment in parallel corpus to project language annotations such as Part-of-Speech tags and dependency relation from high-resource languages to low-resource languages. We use a parallel corpus of Bible translations, including 1,444 translations in 986 languages, and a well-developed parser is used to annotate source languages (English, French, German, and Czech). READ MORE
-
2. Exploring implications of the EU Taxonomy on funding and disclosure for Swedish SMEs
University essay from SLU/Dept. of EconomicsAbstract : In 2019 the EU taxonomy was launched as a classification system that aims to provide a common language and framework for sustainable finance. The purpose is to guide investors and businesses to identify environmentally sustainable economic activities to support the transition towards a low-carbon, resource-efficient economy by 2050 within the EU. READ MORE
-
3. Head-to-head Transfer Learning Comparisons made Possible : A Comparative Study of Transfer Learning Methods for Neural Machine Translation of the Baltic Languages
University essay from Uppsala universitet/Institutionen för lingvistik och filologiAbstract : The struggle of training adequate MT models using data-hungry NMT frameworks for low-resource language pairs has created a need to alleviate the scarcity of sufficiently large parallel corpora. Different transfer learning methods have been introduced as possible solutions to this problem, where a new model for a target task is initialized using parameters learned from some other high-resource task. READ MORE
-
4. Context-aware Swedish Lexical Simplification : Using pre-trained language models to propose contextually fitting synonyms
University essay from Linköpings universitet/Institutionen för datavetenskapAbstract : This thesis presents the development and evaluation of context-aware Lexical Simplification (LS) systems for the Swedish language. In total three versions of LS models, LäsBERT, LäsBERT-baseline, and LäsGPT, were created and evaluated on a newly constructed Swedish LS evaluation dataset. READ MORE
-
5. Text Classification using the Teacher- Student Chatroom Corpus
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Advancements in Artificial Intelligence, especially in the field of natural language processing have opened new possibilities for educational chatbots. One of these is a chatbot that can simulate a conversation between the teacher and the student for continuous learner support. READ MORE