Essays about: "Multi-Task Learning"
Showing result 1 - 5 of 32 essays containing the words Multi-Task Learning.
-
1. Automatic Semantic Role Labelling (SRL) in Swedish
University essay from Göteborgs universitet/Institutionen för data- och informationsteknikAbstract : In this paper, using deep learning networks, the first end-to-end semantic role labelling model (SRL) has been developed for Swedish texts. This Swedish SRL model can, with a given Swedish sentence, perform trigger identification, frame classification and argument extraction tasks automatically in a series. READ MORE
-
2. Natural Language Inference Transfer Learning in a Multi-Task Contract Dataset : In the Case of ContractNLI: a Document Information Extraction System
University essay from Uppsala universitet/Institutionen för lingvistik och filologiAbstract : This thesis investigates the enhancement of legal contract Natural Language Inference (NLI) classification through supervised fine-tuning on general domain NLI, in the case of ContractNLI and Span NLI BERT (Koreeda and Manning, 2021), a multi-task document information extraction dataset and framework. Annotated datasets of a specific professional domain are scarce due to the high time and labour cost required to create them. READ MORE
-
3. Multi-Scale Task Dynamics in Transfer and Multi-Task Learning : Towards Efficient Perception for Autonomous Driving
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Autonomous driving technology has the potential to revolutionize the way we think about transportation and its impact on society. Perceiving the environment is a key aspect of autonomous driving, which involves multiple computer vision tasks. READ MORE
-
4. Metadata assisted finetuning with largepre-trained language models forabstractive text summarization : Multi-task finetuning with abstractive text summarization and categoryclassification
University essay from Umeå universitet/Institutionen för datavetenskapAbstract : Text summarization is time-consuming for humans to complete but is still required in many areas. Recent progress in machine learning research, especially in the natural language domain, has produced promising results. READ MORE
-
5. Cross-Lingual and Genre-Supervised Parsing and Tagging for Low-Resource Spoken Data
University essay from Uppsala universitet/Institutionen för lingvistik och filologiAbstract : 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. READ MORE