Few-shot Learning with Prompting mthods

Few-shot Learning with Prompting mthods


Few-shot Learning with Prompting mthods

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Few-shot Learning with Prompting mthods

ارائه دهنده: Provider: Morteza Bahrami

اساتید راهنما: Supervisors: Dr. Muharram Mansoorizadeh - Dr. Hassan Khotanlou

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Dr. Mir Hossein Dezfoulian - Dr. Hassan Bashiri

زمان و تاریخ ارائه: Time and date of presentation: 2023/9/19 - 09:00

مکان ارائه: Place of presentation: Facualy of Engineering - Class No. 27

چکیده: Abstract: Today, in natural language processing, labeled data is important, however, getting adequate amount of data is a challenging step. There are many tasks for which it is difficult to obtain the required training data. For example, in machine translation, we need to prepare a lot of data in the target language, so that the work performance is acceptable. We may not be able to collect useful data in the target language. Hence, we need to use few-shot learning. Recently, a method called prompting has evolved, in which text inputs are converted into text with a new structure using a certain format, which has a blank space. Given the prompted text, a pre-trained language model replaces the space with the best word. Prompting can help us in the field of few-shot learning; even in cases where there is no data, i.e. zero-shot learning. Recent works use large language models such as GPT-2 and GPT-3, with the prompting method, performed tasks such as machine translation. These efforts do not use any labeled training data. But these types of models with a massive number of parameters require powerful hardware. In this research, a Prompt-based method for few-shot learning has been introduced. The presented method is based on Pattern-Exploiting Training (PET). PET performs few-shot learning with good performance by using small language models such as RoBERTa. Based on the obtained results, the presented method has achieved acceptable results by using PET and Prompt engineering and Answer engineering as well as performing various processing in textual data.

فایل: ّFile: