An information retrieval model based on interaction features and neural networks / Fadel Alhassan
As the state-of-the-art for ad-hoc retrieval, the interaction-based approach represents the interaction between the query and the document through the semantic similarities of their words. The constructed interaction structure is then passed into a deep learning model for feature extraction which in...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/10711/ http://studentsrepo.um.edu.my/10711/1/Fadel_Alhassan.pdf http://studentsrepo.um.edu.my/10711/2/Fadel_Alhassan_%E2%80%93_Dissertation.pdf |
| _version_ | 1848774209965129728 |
|---|---|
| author | Fadel , Alhassan |
| author_facet | Fadel , Alhassan |
| author_sort | Fadel , Alhassan |
| building | UM Research Repository |
| collection | Online Access |
| description | As the state-of-the-art for ad-hoc retrieval, the interaction-based approach represents the interaction between the query and the document through the semantic similarities of their words. The constructed interaction structure is then passed into a deep learning model for feature extraction which in turn are passed into another deep learning model for textual documents ranking. As far as we know, no study has yet identified how relevance matches may appear in the interaction structure and what features reflect that matches. Instead, the majority of the proposed models are based on the hypothesis that relevance matches are following some fixed visual patterns in the interaction matrix. Therefore, most of them are utilizing deep learning techniques for visual pattern recognition for features extraction. This features extraction approach affects the proposed models’ performance and simplicity. This work starts with an analytical study to identify a set of features called the interaction features which reflect how relevance matches may appear in the interaction matrix. Accordingly, a new approach for features extraction and documents ranking is proposed. Interestingly, the study found that the interaction features do not follow any specific visual pattern and therefore it suggests that deep learning techniques are not the most effective approach for the feature extraction task. Instead, a set of manually designed functions are proposed and a shallow neural ranking model was developed. The experiments results confirm the previous finding and show that, though less complex and more efficient, our model was able to outperform two baselines and give a close performance to the state-of-the-art model even without using some important IR factors like term importance. |
| first_indexed | 2025-11-14T13:54:40Z |
| format | Thesis |
| id | um-10711 |
| institution | University Malaya |
| institution_category | Local University |
| last_indexed | 2025-11-14T13:54:40Z |
| publishDate | 2019 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | um-107112020-01-18T02:35:07Z An information retrieval model based on interaction features and neural networks / Fadel Alhassan Fadel , Alhassan QA75 Electronic computers. Computer science As the state-of-the-art for ad-hoc retrieval, the interaction-based approach represents the interaction between the query and the document through the semantic similarities of their words. The constructed interaction structure is then passed into a deep learning model for feature extraction which in turn are passed into another deep learning model for textual documents ranking. As far as we know, no study has yet identified how relevance matches may appear in the interaction structure and what features reflect that matches. Instead, the majority of the proposed models are based on the hypothesis that relevance matches are following some fixed visual patterns in the interaction matrix. Therefore, most of them are utilizing deep learning techniques for visual pattern recognition for features extraction. This features extraction approach affects the proposed models’ performance and simplicity. This work starts with an analytical study to identify a set of features called the interaction features which reflect how relevance matches may appear in the interaction matrix. Accordingly, a new approach for features extraction and documents ranking is proposed. Interestingly, the study found that the interaction features do not follow any specific visual pattern and therefore it suggests that deep learning techniques are not the most effective approach for the feature extraction task. Instead, a set of manually designed functions are proposed and a shallow neural ranking model was developed. The experiments results confirm the previous finding and show that, though less complex and more efficient, our model was able to outperform two baselines and give a close performance to the state-of-the-art model even without using some important IR factors like term importance. 2019-07 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/10711/1/Fadel_Alhassan.pdf application/pdf http://studentsrepo.um.edu.my/10711/2/Fadel_Alhassan_%E2%80%93_Dissertation.pdf Fadel , Alhassan (2019) An information retrieval model based on interaction features and neural networks / Fadel Alhassan. Masters thesis, University of Malaya. http://studentsrepo.um.edu.my/10711/ |
| spellingShingle | QA75 Electronic computers. Computer science Fadel , Alhassan An information retrieval model based on interaction features and neural networks / Fadel Alhassan |
| title | An information retrieval model based on interaction features and neural networks / Fadel Alhassan |
| title_full | An information retrieval model based on interaction features and neural networks / Fadel Alhassan |
| title_fullStr | An information retrieval model based on interaction features and neural networks / Fadel Alhassan |
| title_full_unstemmed | An information retrieval model based on interaction features and neural networks / Fadel Alhassan |
| title_short | An information retrieval model based on interaction features and neural networks / Fadel Alhassan |
| title_sort | information retrieval model based on interaction features and neural networks / fadel alhassan |
| topic | QA75 Electronic computers. Computer science |
| url | http://studentsrepo.um.edu.my/10711/ http://studentsrepo.um.edu.my/10711/1/Fadel_Alhassan.pdf http://studentsrepo.um.edu.my/10711/2/Fadel_Alhassan_%E2%80%93_Dissertation.pdf |