Essays about: "low-resource language"

Showing result 11 - 15 of 30 essays containing the words low-resource language.

  1. 11. Task-agnostic knowledge distillation of mBERT to Swedish

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

    Author : Added Kina; [2022]
    Keywords : Natural Language Processing; Transformers; Knowledge Distillation; BERT; Multilingual Models; Cross-Lingual Transfer; Naturlig bearbetning av språk; Transformatorer; Kunskapsdestillation; BERT; Flerspråkiga modeller; Tvärspråklig inlärningsöverföring;

    Abstract : Large transformer models have shown great performance in multiple natural language processing tasks. However, slow inference, strong dependency on powerful hardware, and large energy consumption limit their availability. READ MORE

  3. 12. Towards a Language Model for Stenography : A Proof of Concept

    University essay from Uppsala universitet/Institutionen för lingvistik och filologi

    Author : Naomi Johanna Langstraat; [2022]
    Keywords : stenography; language model; GPT-2; GPT; grapheme-to-phoneme; G2P; low-resource; perplexity; compression;

    Abstract : The availability of the stenographic manuscripts of Astrid Lindgren have sparked an interest in the creation of a language model for stenography. By its very nature stenography is low-resource and the unavailability of data requires a tool for using normal data. READ MORE

  4. 13. Investigating Few-Shot Transfer Learning for Address Parsing : Fine-Tuning Multilingual Pre-Trained Language Models for Low-Resource Address Segmentation

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

    Author : Hrafndís Heimisdóttir; [2022]
    Keywords : Address Parsing; Address Segmentation; Few-Shot Learning; Transfer Learning; Named Entity Recognition; Adressavkodning; Adress Segmentering; Inlärning med Få Exempel; Överföringsinlärning;

    Abstract : Address parsing is the process of splitting an address string into its different address components, such as street name, street number, et cetera. Address parsing has been quite extensively researched and there exist some state-ofthe-art address parsing solutions, mostly unilingual. READ MORE

  5. 14. Multilingual Speech Emotion Recognition using pretrained models powered by Self-Supervised Learning

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

    Author : Felix Luthman; [2022]
    Keywords : Speech; Audio; Emotion Recognition; Cross-lingual; Multilingual; Self- Supervised Learning; Wav2vec 2.0; HuBERT; UniSpeech; UniSpeech-SAT; WavLM; Språk; Ljud; Känsloigenkänning; Tvärspråklig; Flerspråkig; Själv-Övervakad Inlärning; Wav2vec 2.0; HuBERT; UniSpeech; UniSpeech-SAT; WavLM;

    Abstract : Society is based on communication, for which speech is the most prevalent medium. In day to day interactions we talk to each other, but it is not only the words spoken that matters, but the emotional delivery as well. Extracting emotion from speech has therefore become a topic of research in the area of speech tasks. READ MORE

  6. 15. Improving BERTScore for Machine Translation Evaluation Through Contrastive Learning

    University essay from Uppsala universitet/Institutionen för lingvistik och filologi

    Author : Oreen Yousuf; [2022]
    Keywords : machine translation; evaluation; BERTScore; contrastive learning; SimCSE; Hausa; Somali; Chinese;

    Abstract : Since the advent of automatic evaluation, tasks within Natural Language Processing (NLP), including Machine Translation, have been able to better utilize both time and labor resources. Later, multilingual pre-trained models (MLMs)have uplifted many languages’ capacity to participate in NLP research. READ MORE