Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Niu, Shuzi"'
Despite recommender systems play a key role in network content platforms, mining the user's interests is still a significant challenge. Existing works predict the user interest by utilizing user behaviors, i.e., clicks, views, etc., but current solut
Externí odkaz:
http://arxiv.org/abs/2302.09971
Autor:
Dong, Qian, Liu, Yiding, Cheng, Suqi, Wang, Shuaiqiang, Cheng, Zhicong, Niu, Shuzi, Yin, Dawei
Passage re-ranking is to obtain a permutation over the candidate passage set from retrieval stage. Re-rankers have been boomed by Pre-trained Language Models (PLMs) due to their overwhelming advantages in natural language understanding. However, exis
Externí odkaz:
http://arxiv.org/abs/2204.11673
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yield
Externí odkaz:
http://arxiv.org/abs/1802.02032
We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects. The language is human-written and less noisy. The dialogues in the dataset reflect our daily communication way and cover various topics about ou
Externí odkaz:
http://arxiv.org/abs/1710.03957
Autor:
Shen, Xiaoyu, Su, Hui, Li, Yanran, Li, Wenjie, Niu, Shuzi, Zhao, Yang, Aizawa, Akiko, Long, Guoping
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems. However, these latent variables are highly randomized, leading to uncontrollable generated responses. In this paper, we propose a framew
Externí odkaz:
http://arxiv.org/abs/1705.00316
This paper addresses the problem of rank aggregation, which aims to find a consensus ranking among multiple ranking inputs. Traditional rank aggregation methods are deterministic, and can be categorized into explicit and implicit methods depending on
Externí odkaz:
http://arxiv.org/abs/1309.6852
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Data Science & Engineering; Mar2022, Vol. 7 Issue 1, p30-43, 14p
Autor:
Niu, Shuzi1 niushuzi@software.ict.ac.cn, Lan, Yanyan1 lanyanyan@ict.ac.cn, Guo, Jiafeng1 guojiafeng@ict.ac.cn, Wan, Shengxian1 shengxianwan@software.ict.ac.cn, Cheng, Xueqi1 cxq@ict.ac.cn
Publikováno v:
Information Retrieval Journal. Jun2015, Vol. 18 Issue 3, p215-245. 31p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.