Design and implementation of a response retrieval and reranking system
| dc.contributor | Graduate Program in Electrical and Electronic Engineering. | |
| dc.contributor.advisor | Saraçlar, Murat. | |
| dc.contributor.author | Deveci, Mustafa Can. | |
| dc.date.accessioned | 2023-10-15T07:18:17Z | |
| dc.date.available | 2023-10-15T07:18:17Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | In this master’s thesis, we started with a baseline response retrieval and re ranking system that is composed of two steps: BM25 retrieval and BERT re-ranking. After investigating the effects of several parameters and BERT model size on the base line approach, a novel retrieval and re-ranking system with TF- IDF retrieval and Cross Encoder re-ranking steps was designed and implemented. With the application of Deep Learning models to the re-ranking step, consistent ranking performance improvements have been observed. The research focus of this thesis is a comparative performance study of different Transformer models. In the experiments carried on in this thesis, we showed that smaller transformer models can out- perform larger models. Additionally, this designed re-ranking system was re-purposed for a Question Answering task where the answer for a given question is searched as a subset of a passage. Even though the re-ranking system was directly used without undergoing any modifications regarding the QA task, promising results that are worth further research have been attained. | |
| dc.format.pages | xiii, 69 leaves | |
| dc.identifier.other | EE 2022 D48 | |
| dc.identifier.uri | https://digitalarchive.library.bogazici.edu.tr/handle/123456789/19747 | |
| dc.publisher | Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2022. | |
| dc.subject.lcsh | Electric transformers. | |
| dc.title | Design and implementation of a response retrieval and reranking system |
Files
Original bundle
1 - 1 of 1