Abstract
Dataset search aims to find datasets that are relevant to a keyword query. Existing dataset search engines rely on conventional sparse retrieval models (e.g., BM25). Dense models (e.g., BERT-based) remain under-investigated for two reasons: the limited availability of labeled data for fine-tuning such a deep neural model, and its limited input capacity relative to the large size of a dataset. To fill the gap, in this paper, we study dense re-ranking for RDF dataset search. Our re-ranking model encodes the metadata of RDF datasets and also their actual RDF data—by extracting a small yet representative subset of data to accommodate large datasets. To address the insufficiency of training data, we adopt a coarse-to-fine tuning strategy where we warm up the model with weak supervision from a large set of automatically generated queries and relevance labels. Experiments on the ACORDAR test collection demonstrate the effectiveness of our approach, which considerably improves the retrieval accuracy of existing sparse models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
- 10.
- 11.
References
Anadiotis, A.G., et al.: Graph integration of structured, semistructured and unstructured data for data journalism. Inf. Syst. 104, 101846 (2022). https://doi.org/10.1016/j.is.2021.101846
Benjelloun, O., Chen, S., Noy, N.F.: Google dataset search by the numbers. In: ISWC 2020, vol. 12507, pp. 667–682 (2020). https://doi.org/10.1007/978-3-030-62466-8_41
Brickley, D., Burgess, M., Noy, N.F.: Google dataset search: building a search engine for datasets in an open Web ecosystem. In: WWW 2019, pp. 1365–1375 (2019). https://doi.org/10.1145/3308558.3313685
Cebiric, S., Goasdoué, F., Kondylakis, H., Kotzinos, D., Manolescu, I., Troullinou, G., Zneika, M.: Summarizing semantic graphs: a survey. VLDB J. 28(3), 295–327 (2019). https://doi.org/10.1007/s00778-018-0528-3
Chapman, A., Simperl, E., Koesten, L., Konstantinidis, G., Ibáñez, L., Kacprzak, E., Groth, P.: Dataset search: a survey. VLDB J. 29(1), 251–272 (2020). https://doi.org/10.1007/s00778-019-00564-x
Chen, J., Wang, X., Cheng, G., Kharlamov, E., Qu, Y.: Towards more usable dataset search: From query characterization to snippet generation. In: CIKM 2019, pp. 2445–2448 (2019). https://doi.org/10.1145/3357384.3358096
Chen, J., Chen, Q., Li, D., Huang, Y.: Sedr: segment representation learning for long documents dense retrieval. CoRR abs/2211.10841 (2022). https://doi.org/10.48550/arXiv.2211.10841
Cheng, G., Jin, C., Ding, W., Xu, D., Qu, Y.: Generating illustrative snippets for open data on the Web. In: WSDM 2017, pp. 151–159 (2017). https://doi.org/10.1145/3018661.3018670
Cheng, G., Jin, C., Qu, Y.: HIEDS: a generic and efficient approach to hierarchical dataset summarization. In: IJCAI 2016, pp. 3705–3711 (2016)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019, vol. 1, pp. 4171–4186 (2019). https://doi.org/10.18653/v1/n19-1423
Izacard, G., et al.: Unsupervised dense information retrieval with contrastive learning. CoRR abs/2112.09118 (2021). 10.48550/arXiv.2112.09118
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: EMNLP 2020, pp. 6769–6781 (2020). https://doi.org/10.18653/v1/2020.emnlp-main.550
Kato, M.P., Ohshima, H., Liu, Y., Chen, H.: A test collection for ad-hoc dataset retrieval. In: SIGIR 2021, pp. 2450–2456 (2021). https://doi.org/10.1145/3404835.3463261
Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: SIGIR 2020, pp. 39–48 (2020). https://doi.org/10.1145/3397271.3401075
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR 2015 (2015)
Koesten, L.M., Kacprzak, E., Tennison, J.F.A., Simperl, E.: The trials and tribulations of working with structured data - a study on information seeking behaviour. In: CHI 2017, pp. 1277–1289 (2017). https://doi.org/10.1145/3025453.3025838
Lin, J., Nogueira, R.F., Yates, A.: Pretrained Transformers for Text Ranking: BERT and Beyond. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers, San Rafael (2021). https://doi.org/10.2200/S01123ED1V01Y202108HLT053
Lin, T., et al.: ACORDAR: a test collection for ad hoc content-based (RDF) dataset retrieval. In: SIGIR 2022, pp. 2981–2991 (2022). https://doi.org/10.1145/3477495.3531729
Liu, D., Cheng, G., Liu, Q., Qu, Y.: Fast and practical snippet generation for RDF datasets. ACM Trans. Web 13(4), 19:1–19:38 (2019). https://doi.org/10.1145/3365575
Liu, Q., Cheng, G., Gunaratna, K., Qu, Y.: Entity summarization: state of the art and future challenges. J. Web Semant. 69, 100647 (2021). https://doi.org/10.1016/j.websem.2021.100647
Luo, H., Li, S., Gao, M., Yu, S., Glass, J.R.: Cooperative self-training of machine reading comprehension. In: NAACL 2022, pp. 244–257 (2022). https://doi.org/10.18653/v1/2022.naacl-main.18
Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: ACL 2009, pp. 1003–1011 (2009)
Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. In: CoCo 2016, vol. 1773 (2016)
Pietriga, E., et al.: Browsing linked data catalogs with LODAtlas. In: ISWC 2018, pp. 137–153 (2018). https://doi.org/10.1007/978-3-030-00668-6_9
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1-140:67 (2020)
Robertson, S., Zaragoza, H.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr. 3(4), 333–389 (2009). https://doi.org/10.1561/1500000019
Wang, X., Cheng, G., Kharlamov, E.: Towards multi-facet snippets for dataset search. In: PROFILES & SEMEX 2019, pp. 1–6 (2019)
Wang, X., et al.: PCSG: pattern-coverage snippet generation for RDF datasets. In: ISWC 2021, pp. 3–20 (2021). https://doi.org/10.1007/978-3-030-88361-4_1
Wang, X., Cheng, G., Pan, J.Z., Kharlamov, E., Qu, Y.: BANDAR: benchmarking snippet generation algorithms for (RDF) dataset search. IEEE Trans. Knowl. Data Eng. 35(2), 1227–1241 (2023). https://doi.org/10.1109/TKDE.2021.3095309
Wang, X., Lin, T., Luo, W., Cheng, G., Qu, Y.: CKGSE: a prototype search engine for chinese knowledge graphs. Data Intell. 4(1), 41–65 (2022). https://doi.org/10.1162/dint_a_00118
Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: ICLR 2021 (2021). https://openreview.net/forum?id=zeFrfgyZln
Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives. In: SIGIR 2021, pp. 1503–1512 (2021). https://doi.org/10.1145/3404835.3462880
Zhao, W.X., Liu, J., Ren, R., Wen, J.: Dense text retrieval based on pretrained language models: a survey. CoRR abs/2211.14876 (2022). https://doi.org/10.48550/arXiv.2211.14876
Acknowledgements
This work was supported by the NSFC (62072224).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Q. et al. (2023). Dense Re-Ranking with Weak Supervision for RDF Dataset Search. In: Payne, T.R., et al. The Semantic Web – ISWC 2023. ISWC 2023. Lecture Notes in Computer Science, vol 14265. Springer, Cham. https://doi.org/10.1007/978-3-031-47240-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-47240-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47239-8
Online ISBN: 978-3-031-47240-4
eBook Packages: Computer ScienceComputer Science (R0)