Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language
This thesis is submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science, 2024.
| 第一著者: | |
|---|---|
| その他の著者: | |
| フォーマット: | 学位論文 |
| 言語: | English |
| 出版事項: |
Brac University
2024
|
| 主題: | |
| オンライン･アクセス: | http://hdl.handle.net/10361/24194 |
| id |
10361-24194 |
|---|---|
| record_format |
dspace |
| spelling |
10361-241942024-09-26T21:02:38Z Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language Joaa, A.F.M. Mohimenul Sadeque, Farig Yousuf Department of Computer Science and Engineering, Brac University Curious learner Transformer Natural language processing Customer service automation Machine learning. Electric transformers. This thesis is submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science, 2024. Cataloged from PDF version of thesis. Includes bibliographical references (pages 48-50). Generative models possess immense potential, but their ability to perform complex calculations is limited by the need to memorize vast amounts of data, leading to computational inefficiencies. Leveraging tools like the Arithmetic Logic Unit using symbolic functions offers a more efficient alternative, enabling faster responses, smaller model sizes, and improved accuracy. We propose a neuro-symbolic generative model to empower natural language models with task execution abilities by integrating functional programming principles. Experiments on our scoped four translation tasks using 98 mathematical functions demonstrated rapid convergence and minimal training time requirements. Our model, containing 111 million trainable parameters, achieved an average accuracy, BLEU score, and perplexity score of 0.85, 0.84, and 5.9, respectively, after training on a T4 GPU for several hours. This neurosymbolic Language Model shows significant potential for various applications, such as NLP-based command line tools, customer service automation, service discovery automation, project code automation, and natural language-based operating systems. A.F.M. Mohimenul Joaa M.Sc. in Computer Science 2024-09-26T03:51:35Z 2024-09-26T03:51:35Z ©2024 2024-02 Thesis ID 21166040 http://hdl.handle.net/10361/24194 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 50 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
Curious learner Transformer Natural language processing Customer service automation Machine learning. Electric transformers. |
| spellingShingle |
Curious learner Transformer Natural language processing Customer service automation Machine learning. Electric transformers. Joaa, A.F.M. Mohimenul Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science, 2024. |
| author2 |
Sadeque, Farig Yousuf |
| author_facet |
Sadeque, Farig Yousuf Joaa, A.F.M. Mohimenul |
| format |
Thesis |
| author |
Joaa, A.F.M. Mohimenul |
| author_sort |
Joaa, A.F.M. Mohimenul |
| title |
Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| title_short |
Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| title_full |
Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| title_fullStr |
Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| title_full_unstemmed |
Curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| title_sort |
curious learner: a generative neuro-symbolic approach for function execution & illustration using natural language |
| publisher |
Brac University |
| publishDate |
2024 |
| url |
http://hdl.handle.net/10361/24194 |
| work_keys_str_mv |
AT joaaafmmohimenul curiouslearneragenerativeneurosymbolicapproachforfunctionexecutionillustrationusingnaturallanguage |
| _version_ |
1814307830830727168 |