Filters








4,861 Hits in 7.6 sec

A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data [article]

Jingang Wang, Junfeng Tian, Long Qiu, Sheng Li, Jun Lang, Luo Si and Man Lan
2018 arXiv   pre-print
This paper proposes a novel multi-task learning approach for improving product title compression with user search log data.  ...  It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce.  ...  Ding Liu with Alibaba Group for their valuable discussions and the anonymous reviewers for their helpful comments.  ... 
arXiv:1801.01725v1 fatcat:upfviymp6rhnxepfna7quuwa2m

A Multi-Task Learning Approach for Improving Product Title Compression with User Search Log Data

Jingang Wang, Junfeng Tian, Long Qiu, Sheng Li, Jun Lang, Luo Si, Man Lan
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This paper proposes a novel multi-task learning approach for improving product title compression with user search log data.  ...  It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce.  ...  Ding Liu with Alibaba Group for their valuable discussions and the anonymous reviewers for their helpful comments.  ... 
doi:10.1609/aaai.v32i1.11264 fatcat:fxpyisq32jbcljmw54j47272nu

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce

Jianguo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu
2019 Proceedings of the 2019 Conference of the North  
In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation in E-Commerce, which innovatively incorporates image information and attribute tags from  ...  MM-GAN poses short title generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view.  ...  (c) Agreement-based MTL (Agree-MTL) which is a multi-task learning approach to improve product title compression with user searching log data.  ... 
doi:10.18653/v1/n19-2009 dblp:conf/naacl/ZhangZLWPGY19 fatcat:ecjx3ohbkjfrlfxtipuagk6c7q

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce [article]

Jian-Guo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu
2019 arXiv   pre-print
In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation in E-Commerce, which innovatively incorporates image information and attribute tags from  ...  MM-GAN poses short title generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view.  ...  (c) Agreement-based MTL (Agree-MTL) which is a multi-task learning approach to improve product title compression with user searching log data.  ... 
arXiv:1904.01735v1 fatcat:cncharlchjaozcosktftf2d7aa

Product Title Refinement via Multi-Modal Generative Adversarial Learning [article]

Jianguo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Ye Liu, Xiuming Pan, Yu Gong, Philip S. Yu
2018 arXiv   pre-print
In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation, which innovatively incorporates image information, attribute tags from the product and  ...  MM-GAN treats short titles generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view.  ...  (c) Agreement-based MTL (Agree-MTL) [16] which is a multi-task learning approach to improve product title compression with user searching log data.  ... 
arXiv:1811.04498v1 fatcat:prwxsoe7g5c3tebvkkx633hdvq

User Multi-Interest Modeling for Behavioral Cognition [article]

Bei Yang, Ke Liu, Xiaoxiao Xu, Renjun Xu, Qinghui Sun, Hong Liu, Huan Xu
2022 arXiv   pre-print
With the help of a novel attention module which can learn multi-interests of user, the second sub-module achieves almost lossless dimensionality reduction.  ...  Representation modeling based on user behavior sequences is an important direction in user cognition. In this study, we propose a novel framework called Multi-Interest User Representation Model.  ...  For each user, the reviewed product titles constitute a sequence of review behaviors.  ... 
arXiv:2110.11337v3 fatcat:siuxbxijvbaylmcoyb5nyqada4

Interest-oriented Universal User Representation via Contrastive Learning [article]

Qinghui Sun, Jie Gu, Bei Yang, XiaoXiao Xu, Renjun Xu, Shangde Gao, Hong Liu, Huan Xu
2021 arXiv   pre-print
It provides a unified framework that allows for long-term or short-term interest representation learning in a data-driven manner. Moreover, a novel multi-interest extraction module is presented.  ...  Universal user representation has received many interests recently, with which we can be free from the cumbersome work of training a specific model for each downstream application.  ...  For each user, the reviewed product titles make up a review behavior sequence.  ... 
arXiv:2109.08865v2 fatcat:ej5tisxhfjhslmqw4z5nuztfoq

M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems [article]

Zeyu Cui, Jianxin Ma, Chang Zhou, Jingren Zhou, Hongxia Yang
2022 arXiv   pre-print
settings' data and can minimize the carbon footprint by avoiding training a separate model from scratch for every task.  ...  The mainstream approach so far is to develop individual algorithms for each domain and each task.  ...  We explore two use cases here: (i) generating search queries for recommending to a user, and (ii) generating new product titles based on user behaviors which tell us what types of products may be popular  ... 
arXiv:2205.08084v2 fatcat:p645he3l7zht3dlrxngo5qcecq

Scaling Law for Recommendation Models: Towards General-purpose User Representations [article]

Kyuyong Shin, Hanock Kwak, Su Young Kim, Max Nihlen Ramstrom, Jisu Jeong, Jung-Woo Ha, Kyung-Min Kim
2022 arXiv   pre-print
We demonstrate that the scaling law is present in user representation learning areas, where the training error scales as a power-law with the amount of computation.  ...  Here we explore the possibility of general-purpose user representation learning by training a universal user encoder at large scales.  ...  We would also like to thank the NAVER Smart Machine Learning (NSML) platform team (Sung et al., 2017; Kim et al., 2018) for their critical work on the software and hardware infrastructure on which all  ... 
arXiv:2111.11294v3 fatcat:ywcd5hvfbfa3djdj5wmapdexym

AutoADR: Automatic Model Design for Ad Relevance [article]

Yiren Chen, Yaming Yang, Hong Sun, Yujing Wang, Yu Xu, Wei Shen, Rong Zhou, Yunhai Tong, Jing Bai, Ruofei Zhang
2020 arXiv   pre-print
Specifically, AutoADR leverages a one-shot neural architecture search algorithm to find a tailored network architecture for Ad Relevance.  ...  We add the model designed by AutoADR as a sub-model into the production Ad Relevance model.  ...  Before applying this architecture to production model, we use a large-scale real-world dataset collected from Microsoft Bing search log to retrain it for further improvement.  ... 
arXiv:2010.07075v1 fatcat:jhvzasllj5dujggc5to64rir2m

Pre-trained Language Model for Web-scale Retrieval in Baidu Search [article]

Yiding Liu, Guan Huang, Jiaxiang Liu, Weixue Lu, Suqi Cheng, Yukun Li, Daiting Shi, Shuaiqiang Wang, Zhicong Cheng, Dawei Yin
2021 arXiv   pre-print
., ERNIE) can largely improve the usability and applicability of our search engine.  ...  In particular, we developed an ERNIE-based retrieval model, which is equipped with 1) expressive Transformer-based semantic encoders, and 2) a comprehensive multi-stage training paradigm.  ...  Specifically, we collect one-month (i.e., tens of billions of) user search logs for post-pretraining.  ... 
arXiv:2106.03373v4 fatcat:bkaz3q5dlrcr7nuxdrcrmgu3ti

Probing Product Description Generation via Posterior Distillation [article]

Haolan Zhan, Hainan Zhang, Hongshen Chen, Lei Shen, Zhuoye Ding, Yongjun Bao, Weipeng Yan, Yanyan Lan
2021 arXiv   pre-print
In product description generation (PDG), the user-cared aspect is critical for the recommendation system, which can not only improve user's experiences but also obtain more clicks.  ...  Finally, we apply a Transformer-based decoding phase with copy mechanism to automatically generate the product description.  ...  Acknowledgements The authors would like to thank Hengyi Cai from Institute of Computing Technology, Chinese Academy of Sciences, and the anonymous reviewers for their constructive comments and suggestions  ... 
arXiv:2103.01594v1 fatcat:3x73nvv2fbho3pweeoru3zk54q

ACE-BERT: Adversarial Cross-modal Enhanced BERT for E-commerce Retrieval [article]

Boxuan Zhang, Chao Wei, Yan Jin, Weiru Zhang
2021 arXiv   pre-print
product including title and image in a common subspace.  ...  These multiple modalities are significant for a retrieval system while providing attracted products for customers.  ...  A example is shown in Fig. 1(a) . When a user is looking for "red dress", a product (in the dotted bounding boxes) with title containing "red dress" is presented to the user.  ... 
arXiv:2112.07209v1 fatcat:fa3fvsvgojeopginqgdijxt3aq

e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce [article]

Wonyoung Shin, Jonghun Park, Taekang Woo, Yongwoo Cho, Kwangjin Oh, Hwanjun Song
2022 arXiv   pre-print
As a backbone for online shopping platforms and inspired by the recent success in representation learning research, we propose a contrastive learning framework that aligns language and visual models using  ...  Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce.  ...  accuracy via multi-task learning, and usage as a transferable backbone model for a new downstream task [1, 2, 47] .  ... 
arXiv:2207.00208v1 fatcat:wotusc7h2rd2lhzvel3hwq7yqm

Learning Fast Matching Models from Weak Annotations [article]

Xue Li, Zhipeng Luo, Hao Sun, Jianjin Zhang, Weihao Han, Xianqi Chu, Liangjie Zhang, Qi Zhang
2019 arXiv   pre-print
and weakly annotated search log data.  ...  According to our experiments, compared with the baseline that directly learns from relevance labels, training by the proposed framework outperforms it by a large margin, and improves data efficiency substantially  ...  A brief description of the product is usually displayed as the title of the LP, called LP title.  ... 
arXiv:1901.10710v3 fatcat:dcjarvjsnzfkdky5xesgebludu
« Previous Showing results 1 — 15 out of 4,861 results