Search Results for author:
Found 92 papers, 24 papers with code
Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and Graph
To capture the relation type inference logic of the paths, we propose to understand the unlabeled conceptual expressions by reconstructing the sentence from the relational graph (graph-to-text generation) in a self-supervised manner.
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.
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.
Clue-Guided Path Exploration: An Efficient Knowledge Base Question-Answering Framework with Low Computational Resource Consumption
In this paper, we introduce a Clue-Guided Path Exploration framework (CGPE) that efficiently merges a knowledge base with an LLM, placing less stringent requirements on the model's capabilities.
Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training
In this work, we introduce the concept of complex text style transfer tasks, and constructed complex text datasets based on two widely applicable scenarios.
FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Prompt
In this paper, we propose a method for handling structured knowledge and scanned documents in incremental pre-training.
CLEVA: Chinese Language Models EVAluation Platform
With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model's capabilities has become an increasingly significant issue.
FedSampling: A Better Sampling Strategy for Federated Learning
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.
PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation
Visualization of the local latent prior well confirms the primary devotion in hidden space of the proposed model.
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
We hope that this project will be the foundation of Chinese cognitive intelligence.
Semi-Supervised Hierarchical Graph Classification
We study the node classification problem in the hierarchical graph where a 'node' is a graph instance.
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.
AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling
Variational Auto-Encoder (VAE) has become the de-facto learning paradigm in achieving representation learning and generation for natural language at the same time.
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.
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.
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.
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.
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.
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.
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.
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.
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.
A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods
In recent years, text summarization methods have attracted much attention again thanks to the researches on neural network models.
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.
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.
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.
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)
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.
Provably Secure Generative Linguistic Steganography
Generative linguistic steganography mainly utilized language models and applied steganographic sampling (stegosampling) to generate high-security steganographic text (stegotext).
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.
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.
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.
Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network
To explore entity pairs that may be implicitly connected by relations, we propose a binary pointer network to extract overlapping relational triples relevant to each word sequentially and retain the information of previously extracted triples in an external memory.
Distribution Matching for Rationalization
The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks.
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.
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.
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.
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.
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.
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.
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.
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.
Named Entity Recognition in Multi-level Contexts
In this paper, we propose a unified framework to incorporate multi-level contexts for named entity recognition.
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.
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-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph
On the one hand, we hide the secret information by coding the path in the knowledge graph, but not the conditional probability of each generated word; on the other hand, we can control the semantic expression of the generated steganographic text to a certain extent.
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.
IStego100K: Large-scale Image Steganalysis Dataset
We hope that this test set can help to evaluate the robustness of steganalysis algorithms.
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.
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.
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
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 Topic-Aware News Representation
The core of our approach is a topic-aware news encoder and a user encoder.
Water Preservation in Soan River Basin using Deep Learning Techniques
Water supplies are crucial for the development of living beings.
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.
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.
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.
Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows
To solve these two challenges, in this paper, combined with the sliding window detection algorithm and Convolution Neural Network we propose a real-time VoIP steganalysis method which based on multi-channel convolution sliding windows.
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.
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.
Clinical Assistant Diagnosis for Electronic Medical Record Based on Convolutional Neural Network
Automatically extracting useful information from electronic medical records along with conducting disease diagnoses is a promising task for both clinical decision support(CDS) and neural language processing(NLP).
RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural Network
Experiments show that on full embedding rate samples, RNN-SM is of high detection accuracy, which remains over 90% even when the sample is as short as 0. 1 s, and is significantly higher than other state-of-the-art methods.
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.
Active Sentiment Domain Adaptation
Instead of the source domain sentiment classifiers, our approach adapts the general-purpose sentiment lexicons to target domain with the help of a small number of labeled samples which are selected and annotated in an active learning mode, as well as the domain-specific sentiment similarities among words mined from unlabeled samples of target domain.
Image Captioning with Object Detection and Localization
Automatically generating a natural language description of an image is a task close to the heart of image understanding.
Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval
Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications.
