no code implementations • CCL 2020 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
We compute a title-body matching score based on the representations of title and body enhanced by their interactions.
no code implementations • CCL 2020 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
In addition, we propose an auxiliary term classification task to predict the types of the matched entity names, and jointly train it with the NER model to fuse both contexts and dictionary knowledge into NER.
no code implementations • 1 Aug 2024 • Zhen Yang, Wenhui Wang, Tao Qi, Peng Zhang, Tianyun Zhang, Ru Zhang, Jianyi Liu, Yongfeng Huang
Then candidate news representation can be formed to match user representation to achieve news recommendation.
no code implementations • 25 Jun 2023 • Tao Qi, Fangzhao Wu, Lingjuan Lyu, Yongfeng Huang, Xing Xie
In this paper, instead of client uniform sampling, we propose a novel data uniform sampling strategy for federated learning (FedSampling), which can effectively improve the performance of federated learning especially when client data size distribution is highly imbalanced across clients.
1 code implementation • 7 Jun 2022 • Tao Qi, Fangzhao Wu, Chuhan Wu, Lingjuan Lyu, Tong Xu, Zhongliang Yang, Yongfeng Huang, Xing Xie
In order to learn a fair unified representation, we send it to each platform storing fairness-sensitive features and apply adversarial learning to remove bias from the unified representation inherited from the biased data.
1 code implementation • Nature Communications 2022 • Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, Tao Qi, Yongfeng Huang, Xing Xie
Graph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation.
Ranked #1 on
Recommendation Systems
on MovieLens 100K
(RMSE metric)
no code implementations • 22 May 2022 • Jingwei Yi, Fangzhao Wu, Huishuai Zhang, Bin Zhu, Tao Qi, Guangzhong Sun, Xing Xie
Federated learning (FL) enables multiple clients to collaboratively train models without sharing their local data, and becomes an important privacy-preserving machine learning framework.
no code implementations • 21 Apr 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, Xing Xie
In this paper, we propose a federated contrastive learning method named FedCL for privacy-preserving recommendation, which can exploit high-quality negative samples for effective model training with privacy well protected.
no code implementations • 10 Apr 2022 • Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang
Existing methods for news recommendation usually model user interest from historical clicked news without the consideration of candidate news.
1 code implementation • 10 Apr 2022 • Tao Qi, Fangzhao Wu, Chuhan Wu, Peijie Sun, Le Wu, Xiting Wang, Yongfeng Huang, Xing Xie
To learn provider-fair representations from biased data, we employ provider-biased representations to inherit provider bias from data.
no code implementations • 10 Apr 2022 • Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang
The core idea of FUM is to concatenate the clicked news into a long document and transform user modeling into a document modeling task with both intra-news and inter-news word-level interactions.
no code implementations • 1 Apr 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Since candidate news selection can be biased, we propose to use a shared candidate-aware user model to match user interest with a real displayed candidate news and a random news, respectively, to learn a candidate-aware user embedding that reflects user interest in candidate news and a candidate-invariant user embedding that indicates intrinsic user interest.
no code implementations • 1 Apr 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Different from existing news recommendation methods that are usually based on point- or pair-wise ranking, in LeaDivRec we propose a more effective list-wise news recommendation model.
no code implementations • 1 Apr 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
In this paper, we propose a semi-supervised fair representation learning approach based on adversarial variational autoencoder, which can reduce the dependency of adversarial fair models on data with labeled sensitive attributes.
no code implementations • 1 Apr 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
In addition, we weight the distillation loss based on the overall prediction correctness of the teacher ensemble to distill high-quality knowledge.
no code implementations • 28 Feb 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
They are usually learned on historical user behavior data to infer user interest and predict future user behaviors (e. g., clicks).
no code implementations • 28 Feb 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
In this paper, we propose a quality-aware news recommendation method named QualityRec that can effectively improve the quality of recommended news.
no code implementations • ACL 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, Xing Xie
In this paper, we propose a very simple yet effective method named NoisyTune to help better finetune PLMs on downstream tasks by adding some noise to the parameters of PLMs before fine-tuning.
no code implementations • 10 Feb 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yanlin Wang, Yuqing Yang, Yongfeng Huang, Xing Xie
To solve the game, we propose a platform negotiation method that simulates the bargaining among platforms and locally optimizes their policies via gradient descent.
no code implementations • 10 Feb 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, Xing Xie
However, existing general FL poisoning methods for degrading model performance are either ineffective or not concealed in poisoning federated recommender systems.
no code implementations • Findings (EMNLP) 2021 • Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie
In this paper, we propose a unified news recommendation framework, which can utilize user data locally stored in user clients to train models and serve users in a privacy-preserving way.
no code implementations • 3 Sep 2021 • Chuhan Wu, Fangzhao Wu, Yang Yu, Tao Qi, Yongfeng Huang, Xing Xie
Two self-supervision tasks are incorporated in UserBERT for user model pre-training on unlabeled user behavior data to empower user modeling.
no code implementations • 20 Aug 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Binxing Jiao, Daxin Jiang, Yongfeng Huang, Xing Xie
We then sample token pairs based on their probability scores derived from the sketched attention matrix to generate different sparse attention index matrices for different attention heads.
no code implementations • 20 Aug 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
News recommendation is often modeled as a sequential recommendation task, which assumes that there are rich short-term dependencies over historical clicked news.
12 code implementations • 20 Aug 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, Xing Xie
In this way, Fastformer can achieve effective context modeling with linear complexity.
Ranked #1 on
News Recommendation
on MIND
(using extra training data)
no code implementations • ACL 2021 • Tao Qi, Fangzhao Wu, Chuhan Wu, Peiru Yang, Yang Yu, Xing Xie, Yongfeng Huang
Instead of a single user embedding, in our method each user is represented in a hierarchical interest tree to better capture their diverse and multi-grained interest in news.
no code implementations • ACL 2021 • Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang
The former is used to capture the personalized user interest in news.
no code implementations • ACL 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
It can effectively reduce the complexity and meanwhile capture global document context in the modeling of each sentence.
1 code implementation • 20 Apr 2021 • Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang
Our method interactively models candidate news and user interest to facilitate their accurate matching.
no code implementations • Findings (ACL) 2022 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Recall and ranking are two critical steps in personalized news recommendation.
1 code implementation • 15 Apr 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Our PLM-empowered news recommendation models have been deployed to the Microsoft News platform, and achieved significant gains in terms of both click and pageview in both English-speaking and global markets.
1 code implementation • 15 Apr 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Most of existing news representation methods learn news representations only from news texts while ignore the visual information in news like images.
no code implementations • Findings (EMNLP) 2021 • Chuhan Wu, Fangzhao Wu, Yang Yu, Tao Qi, Yongfeng Huang, Qi Liu
However, existing language models are pre-trained and distilled on general corpus like Wikipedia, which has some gaps with the news domain and may be suboptimal for news intelligence.
no code implementations • 9 Feb 2021 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Besides, the feed recommendation models trained solely on click behaviors cannot optimize other objectives such as user engagement.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Yubo Chen, Chuhan Wu, Tao Qi, Zhigang Yuan, Yongfeng Huang
In this paper, we propose a unified framework to incorporate multi-level contexts for named entity recognition.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
We learn user representations from browsed news representations, and compute click scores based on user and candidate news representations.
no code implementations • 8 Oct 2020 • Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
We propose a query-value interaction function which can learn query-aware attention values, and combine them with the original values and attention weights to form the final output.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Chuhan Wu, Fangzhao Wu, Tao Qi, Jianxun Lian, Yongfeng Huang, Xing Xie
Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pre-train user models from large-scale unlabeled user behaviors data.
no code implementations • ACL 2020 • Chuhan Wu, Fangzhao Wu, Tao Qi, Xiaohui Cui, Yongfeng Huang
Different from existing pooling methods that use a fixed pooling norm, we propose to learn the norm in an end-to-end manner to automatically find the optimal ones for text representation in different tasks.
2 code implementations • ACL 2020 • Fangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu, Tao Qi, Jianxun Lian, Danyang Liu, Xing Xie, Jianfeng Gao, Winnie Wu, Ming Zhou
News recommendation is an important technique for personalized news service.
no code implementations • 31 Mar 2020 • Suyu Ge, Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Existing news recommendation methods achieve personalization by building accurate news representations from news content and user representations from their direct interactions with news (e. g., click), while ignoring the high-order relatedness between users and news.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie
Extensive experiments on a real-world dataset show the effectiveness of our method in news recommendation model training with privacy protection.
no code implementations • 20 Mar 2020 • Suyu Ge, Fangzhao Wu, Chuhan Wu, Tao Qi, Yongfeng Huang, Xing Xie
Since the labeled data in different platforms usually has some differences in entity type and annotation criteria, instead of constraining different platforms to share the same model, we decompose the medical NER model in each platform into a shared module and a private module.
4 code implementations • IJCNLP 2019 • Chuhan Wu, Fangzhao Wu, Suyu Ge, Tao Qi, Yongfeng Huang, Xing Xie
The core of our approach is a news encoder and a user encoder.
no code implementations • IJCNLP 2019 • Chuhan Wu, Fangzhao Wu, Tao Qi, Suyu Ge, Yongfeng Huang, Xing Xie
In the review content-view, we propose to use a hierarchical model to first learn sentence representations from words, then learn review representations from sentences, and finally learn user/item representations from reviews.
no code implementations • IJCNLP 2019 • Chuhan Wu, Fangzhao Wu, Mingxiao An, Tao Qi, Jianqiang Huang, Yongfeng Huang, Xing Xie
In the user representation module, we propose an attentive multi-view learning framework to learn unified representations of users from their heterogeneous behaviors such as search queries, clicked news and browsed webpages.
no code implementations • WS 2019 • Suyu Ge, Tao Qi, Chuhan Wu, Yongfeng Huang
This paper describes our system for the first and second shared tasks of the fourth Social Media Mining for Health Applications (SMM4H) workshop.
no code implementations • SEMEVAL 2019 • Suyu Ge, Tao Qi, Chuhan Wu, Yongfeng Huang
With the development of the Internet, dialog systems are widely used in online platforms to provide personalized services for their users.
no code implementations • SEMEVAL 2019 • Tao Qi, Suyu Ge, Chuhan Wu, Yubo Chen, Yongfeng Huang
First name: Tao Last name: Qi Email: taoqi. qt@gmail. com Affiliation: Department of Electronic Engineering, Tsinghua University First name: Suyu Last name: Ge Email: gesy17@mails. tsinghua. edu. cn Affiliation: Department of Electronic Engineering, Tsinghua University First name: Chuhan Last name: Wu Email: wuch15@mails. tsinghua. edu. cn Affiliation: Department of Electronic Engineering, Tsinghua University First name: Yubo Last name: Chen Email: chen-yb18@mails. tsinghua. edu. cn Affiliation: Department of Electronic Engineering, Tsinghua University First name: Yongfeng Last name: Huang Email: yfhuang@mail. tsinghua. edu. cn Affiliation: Department of Electronic Engineering, Tsinghua University Toponym resolution is an important and challenging task in the neural language processing field, and has wide applications such as emergency response and social media geographical event analysis.