Sökning: "low-resource language"

Visar resultat 1 - 5 av 31 uppsatser innehållade orden low-resource language.

1. 1. How negation influences word order in languages : Automatic classification of word order preference in positive and negative transitive clauses

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Chen Lyu; [2023]
   Nyckelord :;

   Sammanfattning : 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). LÄS MER

3. 2. Head-to-head Transfer Learning Comparisons made Possible : A Comparative Study of Transfer Learning Methods for Neural Machine Translation of the Baltic Languages

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Mathias Stenlund; [2023]
   Nyckelord :machine translation; transfer learning; Latvian; Lithuanian; low-resource languages; transformers; parent language; child language; comparative study;

   Sammanfattning : 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. LÄS MER

4. 3. Neural maskinöversättning av gawarbati

   Kandidat-uppsats, Stockholms universitet/Avdelningen för datorlingvistik

   Författare :Katarina Gillholm; [2023]
   Nyckelord :Machine translation; neural machine translation; NMT; low resource language; Gawarbati; transfer learning; GPT; Maskinöversättning; neural maskinöversättning; NMT; lågresursspråk; gawarbati; överföringsinlärning; GPT;

   Sammanfattning : Nya neurala modeller har lett till stora framsteg inom maskinöversättning, men fungerar fortfarande sämre på språk som saknar stora mängder parallella data, så kallade lågresursspråk. Gawarbati är ett litet, hotat lågresursspråk där endast 5000 parallella meningar finns tillgängligt. LÄS MER

5. 4. BERTie Bott’s Every Flavor Labels : A Tasty Guide to Developing a Semantic Role Labeling Model for Galician

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Micaella Bruton; [2023]
   Nyckelord :natural language processing; NLP; Galician; low-resource language; low resource language; semantic role labeling; SRL; mBERT; XLM-R; transfer-learning; transfer learning; Spanish; verbal indexing; procesamento de linguaxe natural; NLP; Galego; lingua de recursos limitados; etiquetado de papeis semánticos; SRL; mBERT; XLM-R; aprendizaxe por transferencia; Español; indexación verbal; språkteknologiska verktyg; NLP; naturlig språkbehandling; galiciska; språk med begränsade resurser; semantisk rollmärkning; SRL; mBERT; XLM-R; överföringsinlärning; spanska; verbal indexering; verbalindexering; procesamiento del lenguaje natural; NLP; Gallego; idioma de bajos recursos; etiquetado de roles semánticos; SRL; mBERT; XLM-R; aprendizaje por transferencia; Español; indexación verbal;

   Sammanfattning : For the vast majority of languages, Natural Language Processing (NLP) tools are either absent entirely, or leave much to be desired in their final performance. Despite having nearly 4 million speakers, one such low-resource language is Galician. LÄS MER

7. 5. Cross-Lingual and Genre-Supervised Parsing and Tagging for Low-Resource Spoken Data

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Iliana Fosteri; [2023]
   Nyckelord :dependency parsing; part-of-speech tagging; low-resource languages; transcribed speech; large language models; cross-lingual learning; transfer learning; multi-task learning; Universal Dependencies;

   Sammanfattning : Dealing with low-resource languages is a challenging task, because of the absence of sufficient data to train machine-learning models to make predictions on these languages. One way to deal with this problem is to use data from higher-resource languages, which enables the transfer of learning from these languages to the low-resource target ones. LÄS MER