Abstract
This paper describes our methodology for the identical product mining task organized by the China Conference on Knowledge Graph and Semantic Computing (CCKS) 2022. This identical product mining task has two main challenges: 1) How to perform text representation to refine product representation. 2) How to more effectively combine text representation and image representation. For the first challenge, we propose the K-Gram Exponential Decay scheme in the text representation module to aggregate the information of surrounding words. For the second challenge, we apply conventional multimodal representation learning to combine text representation and image representation to generate the item representation. We view the identical product mining task as a binary classification task for product pairs, for which we adopt sample pair-based contrastive learning. Extensive experiments have demonstrated the effectiveness of our method. We won first place in the competition by utilizing model ensemble and post-processing.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Zhang, N., et al.: AliCG: fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery Data Mining, pp. 3895–3905 (2021). ACM, Virtual Event Singapore. https://doi.org/10.1145/3447548.3467057
Fang, Y., Wang, J., Jia, L., Kin, F.W.: Shopee price match guarantee algorithm based on multimodal learning. In: 2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE), pp. 84–87 IEEE, SC, USA (2021). https://doi.org/10.1109/CSAIEE54046.2021.9543217
Sun, Y., et al.: Circle loss: a unified perspective of pair similarity optimization. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6397–6406 IEEE, Seattle, WA, USA (2020). https://doi.org/10.1109/CVPR42600.2020.00643
Huang, Y., et al.: CurricularFace: adaptive curriculum learning loss for deep face recognition. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5900–5909. IEEE, Seattle, WA, USA (2020). https://doi.org/10.1109/CVPR42600.2020.00594
Tracz, J., Wójcik, P.I., Jasinska-Kobus, K., Belluzzo, R., Mroczkowski, R., Gawlik, I.: BERT-based similarity learning for product matching, pp. 66–75 (2020)
Li, J., Dou, Z., Zhu, Y., Zuo, X., Wen, J.-R.: Deep cross-platform product matching in e-commerce. Inf. Retrieval J. 23(2), 136–158 (2019). https://doi.org/10.1007/s10791-019-09360-1
Li, H., et al.: Path-based deep network for candidate item matching in recommenders. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1493–1502 ACM, Virtual Event Canada (2021). https://doi.org/10.1145/3404835.3462878
Peeters, R., Bizer, C.: Supervised contrastive learning for product matching (2022). https://doi.org/10.1145/3487553.3524254
Wu, C., Wu, F., Huang, Y., Xie, X.: User-as-Graph: user modeling with heterogeneous graph pooling for news recommendation. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, pp. 1624–1630. International Joint Conferences on Artificial Intelligence Organization, Montreal, Canada (2021). https://doi.org/10.24963/ijcai.2021/224
Yu, J., Jiang, J., Yang, L., Xia, R.: Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3342–3352. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.acl-main.306
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. http://arxiv.org/abs/1907.11692 (2019)
Yao, H., Liu, H., Zhang, P.: A novel sentence similarity model with word embedding based on convolutional neural network: sentence similarity model with word embedding based on convolutional neural network. Concurrency Computat. Pract. Exper. 30, e4415 (2018). https://doi.org/10.1002/cpe.4415
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9992–10002. IEEE, Montreal, QC, Canada (2021). https://doi.org/10.1109/ICCV48922.2021.00986
Acknowledgement
This work was supported by the grants from National Natural Science Foundation of China (No. 62072423), and the USTC Research Funds of the Double First-Class Initiative (No. YD2150002009).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Feng, C., Chen, W., Chen, C., Xu, T., Chen, E. (2022). Multimodal Representation Learning-Based Product Matching. In: Zhang, N., Wang, M., Wu, T., Hu, W., Deng, S. (eds) CCKS 2022 - Evaluation Track. CCKS 2022. Communications in Computer and Information Science, vol 1711. Springer, Singapore. https://doi.org/10.1007/978-981-19-8300-9_20
Download citation
DOI: https://doi.org/10.1007/978-981-19-8300-9_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8299-6
Online ISBN: 978-981-19-8300-9
eBook Packages: Computer ScienceComputer Science (R0)