Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Prediction

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10085 - 10096 December 7-11, 2022 ©2022 Association for Computational Linguistics Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions Thong Nguyen1,2, Xiaobao Wu3, Anh Tuan Luu3∗, Cong-Duy Nguyen3, Zhen Hai4, Lidong Bing4 1National University of Singapore, Singapore 2VinAI Research, Vietnam 3Nanyang Technological University, Singapore 4DAMO Academy, Alibaba Group e0998147@u.nus.edu, anhtuan.luu@ntu.edu.sg Abstract Modern Review Helpfulness Prediction sys- tems are dependent upon multiple modalities, typically texts and images. Unfortunately, those contemporary approaches pay scarce at- tention to polish representations of cross-modal relations and tend to suffer from inferior opti- mization. This might cause harm to model’s predictions in numerous cases. To overcome the aforementioned issues, we propose Multi- modal Contrastive Learning for Multimodal Review Helpfulness Prediction (MRHP) prob- lem, concentrating on mutual information be- tween input modalities to explicitly elaborate cross-modal relations. In addition, we intro- duce Adaptive Weighting scheme for our con- trastive learning approach in order to increase flexibility in optimization. Lastly, we propose Multimodal Interaction module to address the unalignment nature of multimodal data, thereby assisting the model in producing more reason- able multimodal representations. Experimental results show that our method outperforms prior baselines and achieves state-of-the-art results on two publicly available benchmark datasets for MRHP problem. 1 Introduction Current e-commerce sites such as Amazon, Ebay, etc., construct review platforms to collect user feed- back concerning their products. These platforms play a fundamental role in online transactions since they help future consumers collect useful reviews which assist them in deciding whether to make the purchase or not. Unfortunately, nowadays the number of user-generated reviews is overwhelming, raising doubts related to the relevance and verac- ity of reviews. Therefore, there is a need to verify the quality of reviews before publishing them to prospective customers. As a result, this inspires a recent surge of interest targeting the Review Help- fulness Prediction (RHP) problem. ∗Corresponding Author Product Information The Cooks Standard 6-Quart Stainless Steel Stockpot with Lid is made with 18/10 stainless steel with an aluminum disc layered in the bottom. The aluminum disc bottom provides even heat distribution and prevents hot spots. Tempered glass lid with steam hole vent makes viewing food easy. Stainless steel riveted handles offer durability. Induction compatible. Works on gas, electric, glass, ceramic, etc. Oven safe to 500F, glass lid to 350F. Dishwasher safe. Review 1 I needed a stainless steel pot for canning my tomatoes. I learned the hard way that you have to use a non-reactive pot or else your end result will be inedible (I thought I was using stainless steel but quickly realized it wasnt) I headed to Amazon and came across this Cooks Standard SS Cookpot with cover and bought it after reading the reviews. I have had it for just under a year and it still looks just as good as the day I bought it. I couldn’t be happier with my purchase! Oh, and by the way, this one actually is stainless steel unlike …

Content truncated to 500 words