A supervised term ranking model for diversity enhanced biomedical information retrieval
Abstract Background The number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle t...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-019-3080-2 |
| _version_ | 1818332179368771584 |
|---|---|
| author | Bo Xu Hongfei Lin Liang Yang Kan Xu Yijia Zhang Dongyu Zhang Zhihao Yang Jian Wang Yuan Lin Fuliang Yin |
| author_facet | Bo Xu Hongfei Lin Liang Yang Kan Xu Yijia Zhang Dongyu Zhang Zhihao Yang Jian Wang Yuan Lin Fuliang Yin |
| author_sort | Bo Xu |
| collection | DOAJ |
| description | Abstract Background The number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle the problem. However, information needs cannot be completely satisfied by directly introducing the existing information retrieval techniques. Therefore, biomedical information retrieval not only focuses on the relevance of search results, but also aims to promote the completeness of the results, which is referred as the diversity-oriented retrieval. Results We address the diversity-oriented biomedical retrieval task using a supervised term ranking model. The model is learned through a supervised query expansion process for term refinement. Based on the model, the most relevant and diversified terms are selected to enrich the original query. The expanded query is then fed into a second retrieval to improve the relevance and diversity of search results. To this end, we propose three diversity-oriented optimization strategies in our model, including the diversified term labeling strategy, the biomedical resource-based term features and a diversity-oriented group sampling learning method. Experimental results on TREC Genomics collections demonstrate the effectiveness of the proposed model in improving the relevance and the diversity of search results. Conclusions The proposed three strategies jointly contribute to the improvement of biomedical retrieval performance. Our model yields more relevant and diversified results than the state-of-the-art baseline models. Moreover, our method provides a general framework for improving biomedical retrieval performance, and can be used as the basis for future work. |
| first_indexed | 2024-12-13T13:31:38Z |
| format | Article |
| id | doaj.art-7a04f26f35ab4502a926e04f44d8247b |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-13T13:31:38Z |
| publishDate | 2019-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-7a04f26f35ab4502a926e04f44d8247b2022-12-21T23:44:09ZengBMCBMC Bioinformatics1471-21052019-12-0120S1611110.1186/s12859-019-3080-2A supervised term ranking model for diversity enhanced biomedical information retrievalBo Xu0Hongfei Lin1Liang Yang2Kan Xu3Yijia Zhang4Dongyu Zhang5Zhihao Yang6Jian Wang7Yuan Lin8Fuliang Yin9Faculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyWISE Lab, School of Public Administration and Law, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyAbstract Background The number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle the problem. However, information needs cannot be completely satisfied by directly introducing the existing information retrieval techniques. Therefore, biomedical information retrieval not only focuses on the relevance of search results, but also aims to promote the completeness of the results, which is referred as the diversity-oriented retrieval. Results We address the diversity-oriented biomedical retrieval task using a supervised term ranking model. The model is learned through a supervised query expansion process for term refinement. Based on the model, the most relevant and diversified terms are selected to enrich the original query. The expanded query is then fed into a second retrieval to improve the relevance and diversity of search results. To this end, we propose three diversity-oriented optimization strategies in our model, including the diversified term labeling strategy, the biomedical resource-based term features and a diversity-oriented group sampling learning method. Experimental results on TREC Genomics collections demonstrate the effectiveness of the proposed model in improving the relevance and the diversity of search results. Conclusions The proposed three strategies jointly contribute to the improvement of biomedical retrieval performance. Our model yields more relevant and diversified results than the state-of-the-art baseline models. Moreover, our method provides a general framework for improving biomedical retrieval performance, and can be used as the basis for future work.https://doi.org/10.1186/s12859-019-3080-2Biomedical information retrievalSupervised query expansionTerm ranking modelDiversity-oriented retrievalMachine learningLearning to rank |
| spellingShingle | Bo Xu Hongfei Lin Liang Yang Kan Xu Yijia Zhang Dongyu Zhang Zhihao Yang Jian Wang Yuan Lin Fuliang Yin A supervised term ranking model for diversity enhanced biomedical information retrieval BMC Bioinformatics Biomedical information retrieval Supervised query expansion Term ranking model Diversity-oriented retrieval Machine learning Learning to rank |
| title | A supervised term ranking model for diversity enhanced biomedical information retrieval |
| title_full | A supervised term ranking model for diversity enhanced biomedical information retrieval |
| title_fullStr | A supervised term ranking model for diversity enhanced biomedical information retrieval |
| title_full_unstemmed | A supervised term ranking model for diversity enhanced biomedical information retrieval |
| title_short | A supervised term ranking model for diversity enhanced biomedical information retrieval |
| title_sort | supervised term ranking model for diversity enhanced biomedical information retrieval |
| topic | Biomedical information retrieval Supervised query expansion Term ranking model Diversity-oriented retrieval Machine learning Learning to rank |
| url | https://doi.org/10.1186/s12859-019-3080-2 |
| work_keys_str_mv | AT boxu asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT hongfeilin asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT liangyang asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT kanxu asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT yijiazhang asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT dongyuzhang asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT zhihaoyang asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT jianwang asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT yuanlin asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT fuliangyin asupervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT boxu supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT hongfeilin supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT liangyang supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT kanxu supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT yijiazhang supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT dongyuzhang supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT zhihaoyang supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT jianwang supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT yuanlin supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval AT fuliangyin supervisedtermrankingmodelfordiversityenhancedbiomedicalinformationretrieval |