Sökning: "Token"
Visar resultat 1 - 5 av 146 uppsatser innehållade ordet Token.
1. Incremental Re-tokenization in BPE-trained SentencePiece Models
Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : This bachelor's thesis in Computer Science explores the efficiency of an incremental re-tokenization algorithm in the context of BPE-trained SentencePiece models used in natural language processing. The thesis begins by underscoring the critical role of tokenization in NLP, particularly highlighting the complexities introduced by modifications in tokenized text. LÄS MER
2. WHO’S AFRAID OF COMPLEXITY? An Exploration of the Influence of Native Language Complexity on L2 Complexity
Master-uppsats, Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteoriSammanfattning : The matter of linguistic complexity has been widely scrutinised in the last few decades, within theoretical linguistics, as well as in second language acquisition studies. A concept introduced in the last half of the previous century, it continues to be a matter of debate in the linguistic field, as it eludes a clear-cut definition and interpretation. LÄS MER
3. Ett akademiskt språkbruk : En jämförande studie av elevers produktiva akademiska ordförråd i kurserna svenska 3 och svenska som andraspråk 3 på gymnasiet
Kandidat-uppsats, Uppsala universitet/Institutionen för nordiska språkSammanfattning : Idag förväntas gymnasieelever utveckla färdigheter i att skriva akademiska texter och använda ett akademiskt språkbruk. Tidigare forskning har undersökt elevtexter i kursen svenska 3 (SVE), men inte kursen svenska som andraspråk 3 (SVA). LÄS MER
4. Detection of insurance fraud using NLP and ML
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : Machine-Learning can sometimes see things we as humans can not. In this thesis we evaluated three different Natural Language Procces-techniques: BERT, word2vec and linguistic analysis (UDPipe), on their performance in detecting insurance fraud based on transcribed audio from phone calls (referred to as audio data) and written text (referred to as text-form data), related to insurance claims. LÄS MER
5. A Study in Describing Complex Words Using Wikipedia's Categorisation System : Adding Descriptive Terms to Increase the Comprehension of Swedish Texts
Master-uppsats, Linköpings universitet/Institutionen för datavetenskapSammanfattning : This thesis offers new input in the field of generating epithets to aid the comprehension of Swedish texts. For whatever reason, a reader might find certain words in a text difficult to understand. LÄS MER