Zobrazeno 1 - 10
of 131
pro vyhledávání: '"Jiang, Yunjiang"'
Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural language processing (NLP) tasks suc
Externí odkaz:
http://arxiv.org/abs/2308.09308
Autor:
Gong, Juan, Chen, Zhenlin, Ma, Chaoyi, Xiao, Zhuojian, Wang, Haonan, Tang, Guoyu, Liu, Lin, Xu, Sulong, Long, Bo, Jiang, Yunjiang
Ranking model plays an essential role in e-commerce search and recommendation. An effective ranking model should give a personalized ranking list for each user according to the user preference. Existing algorithms usually extract a user representatio
Externí odkaz:
http://arxiv.org/abs/2306.05011
Publikováno v:
The Tenth International Conference on Learning Representations (ICLR 2022)
Product quantization (PQ) coupled with a space rotation, is widely used in modern approximate nearest neighbor (ANN) search systems to significantly compress the disk storage for embeddings and speed up the inner product computation. Existing rotatio
Externí odkaz:
http://arxiv.org/abs/2203.05082
Autor:
Miao, Dadong, Wang, Yanan, Tang, Guoyu, Liu, Lin, Xu, Sulong, Long, Bo, Xiao, Yun, Wu, Lingfei, Jiang, Yunjiang
Recent years have seen a significant amount of interests in Sequential Recommendation (SR), which aims to understand and model the sequential user behaviors and the interactions between users and items over time. Surprisingly, despite the huge succes
Externí odkaz:
http://arxiv.org/abs/2202.00245
Autor:
Zhang, Xueying, Jiang, Yunjiang, Shang, Yue, Cheng, Zhaomeng, Zhang, Chi, Fan, Xiaochuan, Xiao, Yun, Long, Bo
Publikováno v:
SIGIR 2021: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, July 2021, Pages 2146-2150
We propose a novel domain-specific generative pre-training (DS-GPT) method for text generation and apply it to the product titleand review summarization problems on E-commerce mobile display.First, we adopt a decoder-only transformer architecture, wh
Externí odkaz:
http://arxiv.org/abs/2112.08414
Autor:
Zhang, Han, Shen, Hongwei, Qiu, Yiming, Jiang, Yunjiang, Wang, Songlin, Xu, Sulong, Xiao, Yun, Long, Bo, Yang, Wen-Yun
Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches, often separating the two steps of embedding learning and index build
Externí odkaz:
http://arxiv.org/abs/2105.03933
Autor:
Jiang, Yunjiang, Shang, Yue, Li, Rui, Yang, Wen-Yun, Tang, Guoyu, Ma, Chaoyi, Xiao, Yun, Zhao, Eric
Publikováno v:
DLP-KDD 2019
Result relevance scoring is critical to e-commerce search user experience. Traditional information retrieval methods focus on keyword matching and hand-crafted or counting-based numeric features, with limited understanding of item semantic relevance.
Externí odkaz:
http://arxiv.org/abs/2104.12302
Autor:
Li, Rui, Jiang, Yunjiang, Yang, Wenyun, Tang, Guoyu, Wang, Songlin, Ma, Chaoyi, He, Wei, Xiong, Xi, Xiao, Yun, Zhao, Eric Yihong
We introduce deep learning models to the two most important stages in product search at JD.com, one of the largest e-commerce platforms in the world. Specifically, we outline the design of a deep learning system that retrieves semantically relevant i
Externí odkaz:
http://arxiv.org/abs/2103.12982
Autor:
Liu, Ziyang, Cheng, Zhaomeng, Jiang, Yunjiang, Shang, Yue, Xiong, Wei, Xu, Sulong, Long, Bo, Jin, Di
Result relevance prediction is an essential task of e-commerce search engines to boost the utility of search engines and ensure smooth user experience. The last few years eyewitnessed a flurry of research on the use of Transformer-style models and de
Externí odkaz:
http://arxiv.org/abs/2101.04850
Autor:
Jiang, Yunjiang, Shang, Yue, Liu, Ziyang, Shen, Hongwei, Xiao, Yun, Xiong, Wei, Xu, Sulong, Yan, Weipeng, Jin, Di
Relevance has significant impact on user experience and business profit for e-commerce search platform. In this work, we propose a data-driven framework for search relevance prediction, by distilling knowledge from BERT and related multi-layer Transf
Externí odkaz:
http://arxiv.org/abs/2010.10442