Transformer models for translating natural language sentences into formal logical expressions

Date

2024-4-17

Author

Deveci, İbrahim Ethem

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

1839
views

546
downloads

Cite This

Translating natural language sentences into logical expressions has been challenging due to contextual information and the variational complexity of sentences. The task is not straightforward to handle using rule-based and statistical methods. In recent years, a new deep learning architecture, namely the Transformer architecture, has provided new ways to handle what was hard or seemed impossible in natural language processing tasks. The Transformer architecture and language models that are based on it revolutionized the artificial intelligence field of research and changed how we approach natural language processing tasks. In this thesis, we conduct experiments to see whether successful results can be achieved using Transformer models in translating sentences into first-order logic expressions. We evaluate our models in terms of capturing the formal aspects of the expressions, generating well-formed expressions, and generalizability over unseen sentences.

Subject Keywords

First-order logic, Large language models, Natural language processing, Semantic parsing, Transformer architecture

URI

https://hdl.handle.net/11511/109445

Collections

Graduate School of Informatics, Thesis