Please use this identifier to cite or link to this item:
https://elibrary.tucl.edu.np/handle/123456789/18798
Title: | KEYPHRASE DETECTION AND QUESTION GENERATION FROM TEXT USING MACHINE LEARNING |
Authors: | LAMICHHANE, AAYUSH |
Keywords: | Question Generation,;Transformer;Automation, |
Issue Date: | 30-Apr-2023 |
Publisher: | I.O.E. Pulchowk Campus |
Institute Name: | Institute of Engineering |
Level: | Bachelor |
Abstract: | Question Generation may not be as prominent as Question Answering but it still remains a relevant task in NLP. The ability to ask meaningful questions provides evidence towards comprehension within an Artificial Intelligence (AI) model. This makes the task of question generation important in the bigger picture of AI. While existing question generation techniques rely on complex model architectures and additional mechanisms to boost performance, we show that transformer-based fine-tuning techniques can create robust question generating systems using only a single language model,, without the use of additional mechanisms, answer metadata, and extensive features. Some training parameters of our project are : epoch :10, batchsize : 4, learning rate 10e-3.Lastly, we also look into the model’s failure modes and identify possible reasons why the model fails. |
Description: | In recent times, we have increased the interest in automated systems. One of the key field of automated system is use of Natural Language Processing(NLP) to understand and manipulate natural language text. Although, the biggest field in NLP is text summarization and question answering(QA), another equally important field is Question Generation(QG). |
URI: | https://elibrary.tucl.edu.np/handle/123456789/18798 |
Appears in Collections: | Computer Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
AAyush lamichhane et al. be project report electronics & computer eng apr 2023.pdf | 1.82 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.