Search Results for author:
Found 101 papers, 32 papers with code
Named Entity Recognition with Context-Aware Dictionary Knowledge
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.
Clickbait Detection with Style-aware Title Modeling and Co-attention
We compute a title-body matching score based on the representations of title and body enhanced by their interactions.
RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models
More specifically, for each sample we use LLM to generate a user profile description based on user behavior history or off-the-shelf profile features, which is used to guide LLM to play the role of this user and evaluate the relative preference for two recommendation results generated by different models.
Predictive Models in Sequential Recommendations: Bridging Performance Laws with Data Quality Insights
In response, we introduce the Performance Law for SR models, which aims to theoretically investigate and model the relationship between model performance and data quality.
Beyond Utility: Evaluating LLM as Recommender
We intend our evaluation framework and observations to benefit future research on the use of LLMs as recommenders.
StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs
Despite having powerful reasoning and inference capabilities, Large Language Models (LLMs) still need external tools to acquire real-time information retrieval or domain-specific expertise to solve complex tasks, which is referred to as tool learning.
RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing the text generation quality in a wide range of tasks.
ToolACE: Winning the Points of LLM Function Calling
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability.
Performance Law of Large Language Models
Based on only a few key hyperparameters of the LLM architecture and the size of training data, we obtain a quite accurate MMLU prediction of various LLMs with diverse sizes and architectures developed by different organizations in different years.
All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era
Recommender systems (RS) are vital for managing information overload and delivering personalized content, responding to users' diverse information needs.
Entropy Law: The Story Behind Data Compression and LLM Performance
Inspired by the information compression nature of LLMs, we uncover an ``entropy law'' that connects LLM performance with data compression ratio and first-epoch training loss, which reflect the information redundancy of a dataset and the mastery of inherent knowledge encoded in this dataset, respectively.
Multimodal Pretraining and Generation for Recommendation: A Tutorial
This tutorial seeks to provide a thorough exploration of the latest advancements and future trajectories in multimodal pretraining and generation techniques within the realm of recommender systems.
Revisiting the Efficacy of Signal Decomposition in AI-based Time Series Prediction
Time series prediction is a fundamental problem in scientific exploration and artificial intelligence (AI) technologies have substantially bolstered its efficiency and accuracy.
Collaborative-Enhanced Prediction of Spending on Newly Downloaded Mobile Games under Consumption Uncertainty
In summary, our contributions underscore the importance of stable model training frameworks and the efficacy of collaborative-enhanced models in predicting user spending behavior in mobile gaming.
LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations
The lack of training data gives rise to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations.
Play to Your Strengths: Collaborative Intelligence of Conventional Recommender Models and Large Language Models
The rise of large language models (LLMs) has opened new opportunities in Recommender Systems (RSs) by enhancing user behavior modeling and content understanding.
Confidence-Aware Multi-Field Model Calibration
Accurately predicting the probabilities of user feedback, such as clicks and conversions, is critical for advertisement ranking and bidding.
Learning to Edit: Aligning LLMs with Knowledge Editing
Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention.
A Unified Framework for Multi-Domain CTR Prediction via Large Language Models
Click-Through Rate (CTR) prediction is a crucial task in online recommendation platforms as it involves estimating the probability of user engagement with advertisements or items by clicking on them.
Making the Full Model Adaptive: Multi-level Domain Adaptation for Multi-Domain CTR Prediction
We then select them in a domain-aware way to promote informative features for different domains.
Contrastive Multi-view Framework for Customer Lifetime Value Prediction
Accurate customer lifetime value (LTV) prediction can help service providers optimize their marketing policies in customer-centric applications.
How Can Recommender Systems Benefit from Large Language Models: A Survey
In this paper, we conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems.
DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision
Algorithmic fairness has become an important machine learning problem, especially for mission-critical Web applications.
Effective and Efficient Query-aware Snippet Extraction for Web Search
In this paper, we propose an effective query-aware webpage snippet extraction method named DeepQSE, aiming to select a few sentences which can best summarize the webpage content in the context of input query.
FedX: Unsupervised Federated Learning with Cross Knowledge Distillation
This paper presents FedX, an unsupervised federated learning framework.
FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning
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.
A federated graph neural network framework for privacy-preserving personalization
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)
FedCL: Federated Contrastive Learning for Privacy-Preserving Recommendation
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.
News Recommendation with Candidate-aware User Modeling
Existing methods for news recommendation usually model user interest from historical clicked news without the consideration of candidate news.
FUM: Fine-grained and Fast User Modeling for News Recommendation
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.
ProFairRec: Provider Fairness-aware News Recommendation
To learn provider-fair representations from biased data, we employ provider-biased representations to inherit provider bias from data.
End-to-end Learnable Diversity-aware News Recommendation
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.
FairRank: Fairness-aware Single-tower Ranking Framework for News Recommendation
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.
Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder
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.
Unified and Effective Ensemble Knowledge Distillation
In addition, we weight the distillation loss based on the overall prediction correctness of the teacher ensemble to distill high-quality knowledge.
Quality-aware News Recommendation
In this paper, we propose a quality-aware news recommendation method named QualityRec that can effectively improve the quality of recommended news.
Are Big Recommendation Models Fair to Cold Users?
They are usually learned on historical user behavior data to infer user interest and predict future user behaviors (e. g., clicks).
NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better
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 One Left Behind: Inclusive Federated Learning over Heterogeneous Devices
In this way, all the clients can participate in the model learning in FL, and the final model can be big and powerful enough.
Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction
To solve the game, we propose a platform negotiation method that simulates the bargaining among platforms and locally optimizes their policies via gradient descent.
FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Sampling
However, existing general FL poisoning methods for degrading model performance are either ineffective or not concealed in poisoning federated recommender systems.
Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation
We further propose a two-stage knowledge distillation method to improve the efficiency of the large PLM-based news recommendation model while maintaining its performance.
Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation
However, the computation and communication cost of directly learning many existing news recommendation models in a federated way are unacceptable for user clients.
Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving
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.
UserBERT: Contrastive User Model Pre-training
Two self-supervision tasks are incorporated in UserBERT for user model pre-training on unlabeled user behavior data to empower user modeling.
FedKD: Communication Efficient Federated Learning via Knowledge Distillation
Instead of directly communicating the large models between clients and server, we propose an adaptive mutual distillation framework to reciprocally learn a student and a teacher model on each client, where only the student model is shared by different clients and updated collaboratively to reduce the communication cost.
Fastformer: Additive Attention Can Be All You Need
In this way, Fastformer can achieve effective context modeling with linear complexity.
Ranked #1 on
News Recommendation
on MIND
(using extra training data)
Is News Recommendation a Sequential Recommendation Task?
News recommendation is often modeled as a sequential recommendation task, which assumes that there are rich short-term dependencies over historical clicked news.
Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer
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.
Personalized News Recommendation: Methods and Challenges
Instead of following the conventional taxonomy of news recommendation methods, in this paper we propose a novel perspective to understand personalized news recommendation based on its core problems and the associated techniques and challenges.
DebiasGAN: Eliminating Position Bias in News Recommendation with Adversarial Learning
It is important to eliminate the effect of position biases on the recommendation model to accurately target user interests.
HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation
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.
PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity
The former is used to capture the personalized user interest in news.
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers
In addition, we propose a multi-teacher hidden loss and a multi-teacher distillation loss to transfer the useful knowledge in both hidden states and soft labels from multiple teacher PLMs to the student model.
Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling
It can effectively reduce the complexity and meanwhile capture global document context in the modeling of each sentence.
Rethinking InfoNCE: How Many Negative Samples Do You Need?
We estimate the optimal negative sampling ratio using the $K$ value that maximizes the training effectiveness function.
Personalized News Recommendation with Knowledge-aware Interactive Matching
Our method interactively models candidate news and user interest to facilitate their accurate matching.
DebiasedRec: Bias-aware User Modeling and Click Prediction for Personalized News Recommendation
The core of our method includes a bias representation module, a bias-aware user modeling module, and a bias-aware click prediction module.
Empowering News Recommendation with Pre-trained Language Models
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.
MM-Rec: Multimodal News Recommendation
Most of existing news representation methods learn news representations only from news texts while ignore the visual information in news like images.
Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation
Recall and ranking are two critical steps in personalized news recommendation.
FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
To incorporate high-order user-item interactions, we propose a user-item graph expansion method that can find neighboring users with co-interacted items and exchange their embeddings for expanding the local user-item graphs in a privacy-preserving way.
Ranked #2 on
Recommendation Systems
on MovieLens 100K
(RMSE metric)
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application
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.
FeedRec: News Feed Recommendation with Various User Feedbacks
Besides, the feed recommendation models trained solely on click behaviors cannot optimize other objectives such as user engagement.
Neural News Recommendation with Negative Feedback
The dwell time of news reading is an important clue for user interest modeling, since short reading dwell time usually indicates low and even negative interest.
Named Entity Recognition in Multi-level Contexts
In this paper, we propose a unified framework to incorporate multi-level contexts for named entity recognition.
SentiRec: Sentiment Diversity-aware Neural News Recommendation
We learn user representations from browsed news representations, and compute click scores based on user and candidate news representations.
DA-Transformer: Distance-aware Transformer
Since the raw weighted real distances may not be optimal for adjusting self-attention weights, we propose a learnable sigmoid function to map them into re-scaled coefficients that have proper ranges.
Improving Attention Mechanism with Query-Value Interaction
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.
PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision
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.
FedCTR: Federated Native Ad CTR Prediction with Multi-Platform User Behavior Data
On each platform a local user model is used to learn user embeddings from the local user behaviors on that platform.
MIND: A Large-scale Dataset for News Recommendation
News recommendation is an important technique for personalized news service.
Attentive Pooling with Learnable Norms for Text Representation
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.
FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learning
In this paper, we propose a fairness-aware news recommendation approach with decomposed adversarial learning and orthogonality regularization, which can alleviate unfairness in news recommendation brought by the biases of sensitive user attributes.
Graph Enhanced Representation Learning for News Recommendation
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.
Privacy-Preserving News Recommendation Model Learning
Extensive experiments on a real-world dataset show the effectiveness of our method in news recommendation model training with privacy protection.
FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning
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.
Neural News Recommendation with Heterogeneous User Behavior
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.
Neural News Recommendation with Multi-Head Self-Attention
The core of our approach is a news encoder and a user encoder.
Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network
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.
Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN
A significant novelty of the proposed RGAN is that it combines the supervised and regressional convolutional neural network (CNN) with the traditional unsupervised GAN, thus overcoming the common technical barrier in the traditional GANs, which cannot generate data associated with given continuous quantitative labels.
Computational Physics Materials Science Applied Physics
Detecting and Extracting of Adverse Drug Reaction Mentioning Tweets with Multi-Head Self Attention
This paper describes our system for the first and second shared tasks of the fourth Social Media Mining for Health Applications (SMM4H) workshop.
NPA: Neural News Recommendation with Personalized Attention
Since different words and different news articles may have different informativeness for representing news and users, we propose to apply both word- and news-level attention mechanism to help our model attend to important words and news articles.
Neural News Recommendation with Attentive Multi-View Learning
In the user encoder we learn the representations of users based on their browsed news and apply attention mechanism to select informative news for user representation learning.
Ranked #6 on
News Recommendation
on MIND
Neural News Recommendation with Long- and Short-term User Representations
In this paper, we propose a neural news recommendation approach which can learn both long- and short-term user representations.
Ranked #7 on
News Recommendation
on MIND
Neural News Recommendation with Topic-Aware News Representation
The core of our approach is a topic-aware news encoder and a user encoder.
THU\_NGN at SemEval-2019 Task 12: Toponym Detection and Disambiguation on Scientific Papers
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.
THU\_NGN at SemEval-2019 Task 3: Dialog Emotion Classification using Attentional LSTM-CNN
With the development of the Internet, dialog systems are widely used in online platforms to provide personalized services for their users.
Hierarchical User and Item Representation with Three-Tier Attention for Recommendation
In this paper, we propose a hierarchical user and item representation model with three-tier attention to learn user and item representations from reviews for recommendation.
NRPA: Neural Recommendation with Personalized Attention
In this paper we propose a neural recommendation approach with personalized attention to learn personalized representations of users and items from reviews.
Neural Chinese Named Entity Recognition via CNN-LSTM-CRF and Joint Training with Word Segmentation
Besides, the training data for CNER in many domains is usually insufficient, and annotating enough training data for CNER is very expensive and time-consuming.
Chinese Named Entity Recognition
named-entity-recognition
+1
Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization
Luckily, the unlabeled data is usually easy to collect and many high-quality Chinese lexicons are off-the-shelf, both of which can provide useful information for CWS.
Detecting Tweets Mentioning Drug Name and Adverse Drug Reaction with Hierarchical Tweet Representation and Multi-Head Self-Attention
This paper describes our system for the first and third shared tasks of the third Social Media Mining for Health Applications (SMM4H) workshop, which aims to detect the tweets mentioning drug names and adverse drug reactions.
Deep Learning Bandgaps of Topologically Doped Graphene
Moreover, given ubiquitous existence of topologies in materials, this work will stimulate widespread interests in applying deep learning algorithms to topological design of materials crossing atomic, nano-, meso-, and macro- scales.
Materials Science Computational Physics
Neural Chinese Word Segmentation with Dictionary Knowledge
The experimental results on two benchmark datasets validate that our approach can effectively improve the performance of Chinese word segmentation, especially when training data is insufficient.
THU\_NGN at SemEval-2018 Task 2: Residual CNN-LSTM Network with Attention for English Emoji Prediction
Thus, in SemEval-2018 Task 2 an interesting and challenging task is proposed, i. e., predicting which emojis are evoked by text-based tweets.
THU\_NGN at SemEval-2018 Task 10: Capturing Discriminative Attributes with MLP-CNN model
Thus, the aim of SemEval-2018 Task 10 is to predict whether a word is a discriminative attribute between two concepts.
THU\_NGN at SemEval-2018 Task 3: Tweet Irony Detection with Densely connected LSTM and Multi-task Learning
Detecting irony is an important task to mine fine-grained information from social web messages.
THU\_NGN at SemEval-2018 Task 1: Fine-grained Tweet Sentiment Intensity Analysis with Attention CNN-LSTM
In order to address this task, we propose a system based on an attention CNN-LSTM model.
Neural Metaphor Detecting with CNN-LSTM Model
In addition, we compare the performance of the softmax classifier and conditional random field (CRF) for sequential labeling in this task.
THU\_NGN at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases with Deep LSTM
Since the existing valence-arousal resources of Chinese are mainly in word-level and there is a lack of phrase-level ones, the Dimensional Sentiment Analysis for Chinese Phrases (DSAP) task aims to predict the valence-arousal ratings for Chinese affective words and phrases automatically.
