Essays about: "Multilingual BERT"

Showing result 16 - 20 of 22 essays containing the words Multilingual BERT.

1. 16. DistillaBSE: Task-agnostic  distillation of multilingual sentence  embeddings : Exploring deep self-attention distillation with switch transformers

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Boris Bubla; [2021]
   Keywords : Transformers; Knowledge Distillation; Language Agnostic BERT Sentence Embeddings; Natural Language Processing; Switch Transformers; Transformatorer; kunskapsdestillation; språkagnostisk inbäddning av BERT- mening; naturlig bearbetning av språk; switchtransformatorer;

   Abstract : The recent development of massive multilingual transformer networks has resulted in drastic improvements in model performance. These models, however, are so large they suffer from large inference latency and consume vast computing resources. Such features hinder widespread adoption of the models in industry and some academic settings. READ MORE

3. 17. French AXA Insurance Word Embeddings : Effects of Fine-tuning BERT and Camembert on AXA France’s data

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Hend Zouari; [2020]
   Keywords : NLP; Language model; Word embedding; BERT; camemBERT; NLP; Language model; Word embedding; BERT; camemBERT;

   Abstract : We explore in this study the different Natural Language Processing state-of-the art technologies that allow transforming textual data into numerical representation. We go through the theory of the existing traditional methods as well as the most recent ones. READ MORE

4. 18. Context matters : Classifying Swedish texts using BERT's deep bidirectional word embeddings

   University essay from Linköpings universitet/Institutionen för datavetenskap

   Author : Daniel Holmer; [2020]
   Keywords : NLP; text classification; BERT; feature representation; pre-trained language models; transformer networks; fine-tuning;

   Abstract : When classifying texts using a linear classifier, the texts are commonly represented as feature vectors. Previous methods to represent features as vectors have been unable to capture the context of individual words in the texts, in theory leading to a poor representation of natural language. READ MORE

5. 19. Transfer Learning for Multilingual Offensive Language Detection with BERT

   University essay from Uppsala universitet/Institutionen för lingvistik och filologi

   Author : Camilla Casula; [2020]
   Keywords : ;

   Abstract : The popularity of social media platforms has led to an increase in user-generated content being posted on the Internet. Users, masked behind what they perceive as anonymity, can express offensive and hateful thoughts on these platforms, creating a need to detect and filter abusive content. READ MORE

6. 20. Anomaly Detection Across Multiple Languages

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Mastafa Foufa; [2020]
   Keywords : ;

   Abstract : We present Multilingual Anomaly Detector (MAD), a toolkit to detect anomalies insensitive to the use of different languages. Unsupervised anomaly detection on high-dimensional textual data is of great relevance in both machine learning research and industrial applications. READ MORE