Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Pengxiang Cheng"'
Autor:
Dugang Liu, Pengxiang Cheng, Zinan Lin, Xiaolian Zhang, Zhenhua Dong, Rui Zhang, Xiuqiang He, Weike Pan, Zhong Ming
Publikováno v:
ACM Transactions on Information Systems. 41:1-26
Debiased recommendation with a randomized dataset has shown very promising results in mitigating the system-induced biases. However, it still lacks more theoretical insights or an ideal optimization objective function compared with the other more wel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba382bb6bc8d5e5e829859108d22b1c9
https://doi.org/10.1145/3582002
https://doi.org/10.1145/3582002
Publikováno v:
ACM Transactions on Recommender Systems. 1:1-27
How to effectively mitigate the bias of feedback in recommender systems is an important research topic. In this article, we first describe the generation process of the biased and unbiased feedback in recommender systems via two respective causal dia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bea3a7a5935309519fd334bdcc44578c
https://doi.org/10.1145/3568030
https://doi.org/10.1145/3568030
Autor:
Dugang Liu, Pengxiang Cheng, Hong Zhu, Xing Tang, Yanyu Chen, Xiaoting Wang, Weike Pan, Zhong Ming, Xiuqiang He
Publikováno v:
Proceedings of the ACM Web Conference 2023.
Tabular data is one of the most common data storage formats behind many real-world web applications such as retail, banking, and e-commerce. The success of these web applications largely depends on the ability of the employed machine learning model t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::899a672c175ebb2cc570944d9d495d86
https://doi.org/10.1145/3543507.3583382
https://doi.org/10.1145/3543507.3583382
Publikováno v:
RecSys
How to effectively mitigate the bias of feedback in recommender systems is an important research topic. In this paper, we first describe the generation process of the biased and unbiased feedback in recommender systems via two respective causal diagr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e53589aae0826dea3522d25dd324a1f3
https://doi.org/10.1145/3460231.3474263
https://doi.org/10.1145/3460231.3474263
Autor:
Katrin Erk, Pengxiang Cheng
Publikováno v:
AAAI
Implicit arguments, which cannot be detected solely through syntactic cues, make it harder to extract predicate-argument tuples. We present a new model for implicit argument prediction that draws on reading comprehension, casting the predicate-argume
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af2c80f2bcb51080f84b23fdddc1fab2
https://doi.org/10.1609/aaai.v33i01.33016284
https://doi.org/10.1609/aaai.v33i01.33016284
Autor:
Hong Zhu, Jun Xu, Pengxiang Cheng, Xinhua Feng, Guohao Cai, Zhenhua Dong, Xiuqiang He, Ji-Rong Wen
Publikováno v:
RecSys
Most commercial industrial recommender systems have built their closed feedback loops. Though it is helpful in item recommendation and model training, the closed feedback loop may lead to the so-called bias problems, including the position bias, sele
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1972cf0a5b31e05f7bd6bc3e67d7635
https://doi.org/10.1145/3383313.3411552
https://doi.org/10.1145/3383313.3411552
Publikováno v:
SIGIR
Recommender systems are feedback loop systems, which often face bias problems such as popularity bias, previous model bias and position bias. In this paper, we focus on solving the bias problems in a recommender system via a uniform data. Through emp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b5988dd99235c0e4a25d5da199503d2
https://doi.org/10.1145/3397271.3401083
https://doi.org/10.1145/3397271.3401083
Publikováno v:
WWW
Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user. We observe this ubiquitous phenomenon on both public and private d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::916fc3e2b5019e44fe19b05217e11f19
http://arxiv.org/abs/2001.10378
http://arxiv.org/abs/2001.10378
Autor:
Pengxiang Cheng, Katrin Erk
Publikováno v:
AAAI
Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art results, approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a04fe7abddd226280e47210bb1aacbef
http://arxiv.org/abs/1911.04361
http://arxiv.org/abs/1911.04361
Autor:
Pengxiang Cheng, Katrin Erk
Publikováno v:
NAACL-HLT
Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. We propose to train models for implicit argumen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76fe42ae73859d931402cb4c2380b6cd
http://arxiv.org/abs/1802.07226
http://arxiv.org/abs/1802.07226