Search Results for author: Qing He

Found 66 papers, 24 papers with code

Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension

1 code implementation Findings (EMNLP) 2021 Guoxin Yu, Jiwei Li, Ling Luo, Yuxian Meng, Xiang Ao, Qing He

In this paper, we investigate the unified ABSA task from the perspective of Machine Reading Comprehension (MRC) by observing that the aspect and the opinion terms can serve as the query and answer in MRC interchangeably.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

Transformer with Syntactic Position Encoding for Machine Translation

no code implementations RANLP 2021 Yikuan Xie, Wenyong Wang, Mingqian Du, Qing He

It has been widely recognized that syntax information can help end-to-end neural machine translation (NMT) systems to achieve better translation.

Machine Translation NMT +3

Ultra-lightweight Neural Differential DSP Vocoder For High Quality Speech Synthesis

no code implementations19 Jan 2024 Prabhav Agrawal, Thilo Koehler, Zhiping Xiu, Prashant Serai, Qing He

A DSP vocoder often gets a lower audio quality due to consuming over-smoothed acoustic model predictions of approximate representations for the vocal tract.

Speech Synthesis

Multi-Task Learning for Front-End Text Processing in TTS

1 code implementation12 Jan 2024 Wonjune Kang, Yun Wang, Shun Zhang, Arthur Hinsvark, Qing He

We propose a multi-task learning (MTL) model for jointly performing three tasks that are commonly solved in a text-to-speech (TTS) front-end: text normalization (TN), part-of-speech (POS) tagging, and homograph disambiguation (HD).

Language Modelling Multi-Task Learning +3

Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning

1 code implementation25 May 2023 Shuo Yu, Hongyan Xue, Xiang Ao, Feiyang Pan, Jia He, Dandan Tu, Qing He

In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together.

reinforcement-learning Reinforcement Learning (RL)

Attacking Pre-trained Recommendation

1 code implementation6 May 2023 Yiqing Wu, Ruobing Xie, Zhao Zhang, Yongchun Zhu, Fuzhen Zhuang, Jie zhou, Yongjun Xu, Qing He

Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks.

Sequential Recommendation

Self-Supervised Representations for Singing Voice Conversion

no code implementations21 Mar 2023 Tejas Jayashankar, JiLong Wu, Leda Sari, David Kant, Vimal Manohar, Qing He

A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer.

Disentanglement Voice Conversion

Voice-preserving Zero-shot Multiple Accent Conversion

no code implementations23 Nov 2022 Mumin Jin, Prashant Serai, JiLong Wu, Andros Tjandra, Vimal Manohar, Qing He

Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent.

Solving Coupled Differential Equation Groups Using PINO-CDE

2 code implementations1 Oct 2022 Wenhao Ding, Qing He, Hanghang Tong, Qingjing Wang, Ping Wang

This framework integrates engineering dynamics and deep learning technologies and may reveal a new concept for CDEs solving and uncertainty propagation.

Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN

1 code implementation30 Jun 2022 Kuan Li, Yang Liu, Xiang Ao, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He

However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e. g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph.

Customized Conversational Recommender Systems

no code implementations30 Jun 2022 Shuokai Li, Yongchun Zhu, Ruobing Xie, Zhenwei Tang, Zhao Zhang, Fuzhen Zhuang, Qing He, Hui Xiong

In this paper, we propose two key points for CRS to improve the user experience: (1) Speaking like a human, human can speak with different styles according to the current dialogue context.

Meta-Learning Recommendation Systems

Personalized Prompt for Sequential Recommendation

no code implementations19 May 2022 Yiqing Wu, Ruobing Xie, Yongchun Zhu, Fuzhen Zhuang, Xu Zhang, Leyu Lin, Qing He

Specifically, we build the personalized soft prefix prompt via a prompt generator based on user profiles and enable a sufficient training of prompts via a prompt-oriented contrastive learning with both prompt- and behavior-based augmentations.

Contrastive Learning Sequential Recommendation

Selective Fairness in Recommendation via Prompts

1 code implementation10 May 2022 Yiqing Wu, Ruobing Xie, Yongchun Zhu, Fuzhen Zhuang, Xiang Ao, Xu Zhang, Leyu Lin, Qing He

In this work, we define the selective fairness task, where users can flexibly choose which sensitive attributes should the recommendation model be bias-free.

Attribute Fairness +1

User-Centric Conversational Recommendation with Multi-Aspect User Modeling

1 code implementation20 Apr 2022 Shuokai Li, Ruobing Xie, Yongchun Zhu, Xiang Ao, Fuzhen Zhuang, Qing He

In this work, we highlight that the user's historical dialogue sessions and look-alike users are essential sources of user preferences besides the current dialogue session in CRS.

Dialogue Generation Dialogue Understanding +1

CCAT-NET: A Novel Transformer Based Semi-supervised Framework for Covid-19 Lung Lesion Segmentation

no code implementations6 Apr 2022 Mingyang Liu, Li Xiao, Huiqin Jiang, Qing He

In this work, we propose a novel network structure that combines CNN and Transformer for the segmentation of COVID-19 lesions.

Lesion Segmentation Segmentation

Multi-view Multi-behavior Contrastive Learning in Recommendation

1 code implementation20 Mar 2022 Yiqing Wu, Ruobing Xie, Yongchun Zhu, Xiang Ao, Xin Chen, Xu Zhang, Fuzhen Zhuang, Leyu Lin, Qing He

We argue that MBR models should: (1) model the coarse-grained commonalities between different behaviors of a user, (2) consider both individual sequence view and global graph view in multi-behavior modeling, and (3) capture the fine-grained differences between multiple behaviors of a user.

Contrastive Learning

Multi-Representation Adaptation Network for Cross-domain Image Classification

1 code implementation4 Jan 2022 Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Jingwu Chen, Zhiping Shi, Wenjuan Wu, Qing He

Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects.

Classification Domain Adaptation +2

Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection

no code implementations4 Jan 2022 Yongchun Zhu, Dongbo Xi, Bowen Song, Fuzhen Zhuang, Shuai Chen, Xi Gu, Qing He

Thus, in this paper, we further propose a transfer framework to tackle the cross-domain fraud detection problem, which aims to transfer knowledge from existing domains (source domains) with enough and mature data to improve the performance in the new domain (target domain).

Fraud Detection

Neural Hierarchical Factorization Machines for User's Event Sequence Analysis

no code implementations31 Dec 2021 Dongbo Xi, Fuzhen Zhuang, Bowen Song, Yongchun Zhu, Shuai Chen, Dan Hong, Tao Chen, Xi Gu, Qing He

Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance.

Exploiting Bi-directional Global Transition Patterns and Personal Preferences for Missing POI Category Identification

no code implementations31 Dec 2021 Dongbo Xi, Fuzhen Zhuang, Yanchi Liu, HengShu Zhu, Pengpeng Zhao, Chang Tan, Qing He

To this end, in this paper, we propose a novel neural network approach to identify the missing POI categories by integrating both bi-directional global non-personal transition patterns and personal preferences of users.

Recommendation Systems

Domain Adaptation with Category Attention Network for Deep Sentiment Analysis

no code implementations31 Dec 2021 Dongbo Xi, Fuzhen Zhuang, Ganbin Zhou, Xiaohu Cheng, Fen Lin, Qing He

Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via reducing the shift between the data distributions.

Attribute Classification +3

Modelling of Bi-directional Spatio-Temporal Dependence and Users' Dynamic Preferences for Missing POI Check-in Identification

no code implementations31 Dec 2021 Dongbo Xi, Fuzhen Zhuang, Yanchi Liu, Jingjing Gu, Hui Xiong, Qing He

Then, target temporal pattern in combination with user and POI information are fed into a multi-layer network to capture users' dynamic preferences.

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

no code implementations27 Dec 2021 Fuwei Zhang, Zhao Zhang, Xiang Ao, Dehong Gao, Fuzhen Zhuang, Yi Wei, Qing He

The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism.

Cross-Lingual Information Retrieval Retrieval

VocBench: A Neural Vocoder Benchmark for Speech Synthesis

1 code implementation6 Dec 2021 Ehab A. AlBadawy, Andrew Gibiansky, Qing He, JiLong Wu, Ming-Ching Chang, Siwei Lyu

We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.

Speech Synthesis

Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation

1 code implementation NeurIPS 2021 Ying Sun, HengShu Zhu, Chuan Qin, Fuzhen Zhuang, Qing He, Hui Xiong

To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN).

Decision Making

Personalized Transfer of User Preferences for Cross-domain Recommendation

1 code implementation21 Oct 2021 Yongchun Zhu, Zhenwei Tang, Yudan Liu, Fuzhen Zhuang, Ruobing Xie, Xu Zhang, Leyu Lin, Qing He

Specifically, a meta network fed with users' characteristic embeddings is learned to generate personalized bridge functions to achieve personalized transfer of preferences for each user.

Recommendation Systems

Rethinking Pareto Approaches in Constrained Reinforcement Learning

no code implementations29 Sep 2021 Mengda Huang, Feiyang Pan, Jia He, Xiang Ao, Qing He

Constrained Reinforcement Learning (CRL) burgeons broad interest in recent years, which pursues both goals of maximizing long-term returns and constraining costs.

reinforcement-learning Reinforcement Learning (RL)

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback

1 code implementation13 Aug 2021 Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He

The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.

PENS: A Dataset and Generic Framework for Personalized News Headline Generation

1 code implementation ACL 2021 Xiang Ao, Xiting Wang, Ling Luo, Ying Qiao, Qing He, Xing Xie

To build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS).

Headline Generation

GuideBoot: Guided Bootstrap for Deep Contextual Bandits

no code implementations18 Jul 2021 Feiyang Pan, Haoming Li, Xiang Ao, Wei Wang, Yanrong Kang, Ao Tan, Qing He

The proposed method is efficient as it can make decisions on-the-fly by utilizing only one randomly chosen model, but is also effective as we show that it can be viewed as a non-Bayesian approximation of Thompson sampling.

Multi-Armed Bandits Thompson Sampling

Direct speech-to-speech translation with discrete units

1 code implementation ACL 2022 Ann Lee, Peng-Jen Chen, Changhan Wang, Jiatao Gu, Sravya Popuri, Xutai Ma, Adam Polyak, Yossi Adi, Qing He, Yun Tang, Juan Pino, Wei-Ning Hsu

When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass.

Speech-to-Speech Translation Text Generation +1

ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information

3 code implementations ACL 2021 Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng, Xiang Ao, Qing He, Fei Wu, Jiwei Li

Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding.

Language Modelling Machine Reading Comprehension +5

Deep Subdomain Adaptation Network for Image Classification

1 code implementation17 Jun 2021 Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Guolin Ke, Jingwu Chen, Jiang Bian, Hui Xiong, Qing He

The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation.

Classification Domain Adaptation +4

AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction

no code implementations16 Jun 2021 Hao Chen, Fuzhen Zhuang, Li Xiao, Ling Ma, Haiyan Liu, Ruifang Zhang, Huiqin Jiang, Qing He

The encoder can automatically construct the population graph using phenotypic measures which have a positive impact on the final results, and further realizes the fusion of multimodal information.

Disease Prediction text similarity

Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users

no code implementations11 May 2021 Yongchun Zhu, Kaikai Ge, Fuzhen Zhuang, Ruobing Xie, Dongbo Xi, Xu Zhang, Leyu Lin, Qing He

With the advantage of meta learning which has good generalization ability to novel tasks, we propose a transfer-meta framework for CDR (TMCDR) which has a transfer stage and a meta stage.

Meta-Learning Recommendation Systems

Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection

1 code implementation The Web Conference 2021 Yang Liu1, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He

Graph-based fraud detection approaches have escalated lots of attention recently due to the abundant relational information of graph-structured data, which may be beneficial for the detection of fraudsters.

Fraud Detection Node Classification

Multi-rate attention architecture for fast streamable Text-to-speech spectrum modeling

no code implementations1 Apr 2021 Qing He, Zhiping Xiu, Thilo Koehler, JiLong Wu

Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio.

Combat Data Shift in Few-shot Learning with Knowledge Graph

no code implementations27 Jan 2021 Yongchun Zhu, Fuzhen Zhuang, Xiangliang Zhang, Zhiyuan Qi, Zhiping Shi, Juan Cao, Qing He

However, in real-world applications, few-shot learning paradigm often suffers from data shift, i. e., samples in different tasks, even in the same task, could be drawn from various data distributions.

Few-Shot Learning

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge

no code implementations25 Nov 2020 Bichen Wu, Qing He, Peizhao Zhang, Thilo Koehler, Kurt Keutzer, Peter Vajda

More efficient variants of FBWave can achieve up to 109x fewer MACs while still delivering acceptable audio quality.

Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection

no code implementations8 Aug 2020 Dongbo Xi, Bowen Song, Fuzhen Zhuang, Yongchun Zhu, Shuai Chen, Tianyi Zhang, Yuan Qi, Qing He

In this paper, we propose the Dual Importance-aware Factorization Machines (DIFM), which exploits the internal field information among users' behavior sequence from dual perspectives, i. e., field value variations and field interactions simultaneously for fraud detection.

Fraud Detection Management

Graph Factorization Machines for Cross-Domain Recommendation

no code implementations12 Jul 2020 Dongbo Xi, Fuzhen Zhuang, Yongchun Zhu, Pengpeng Zhao, Xiangliang Zhang, Qing He

In this paper, we propose a Graph Factorization Machine (GFM) which utilizes the popular Factorization Machine to aggregate multi-order interactions from neighborhood for recommendation.

Recommendation Systems

A Survey on Knowledge Graph-Based Recommender Systems

no code implementations28 Feb 2020 Qingyu Guo, Fuzhen Zhuang, Chuan Qin, HengShu Zhu, Xing Xie, Hui Xiong, Qing He

On the one hand, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation.

Explainable Recommendation Recommendation Systems

Transfer Learning Toolkit: Primers and Benchmarks

2 code implementations20 Nov 2019 Fuzhen Zhuang, Keyu Duan, Tongjia Guo, Yongchun Zhu, Dongbo Xi, Zhiyuan Qi, Qing He

The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function.

Transfer Learning

A Comprehensive Survey on Transfer Learning

3 code implementations7 Nov 2019 Fuzhen Zhuang, Zhiyuan Qi, Keyu Duan, Dongbo Xi, Yongchun Zhu, HengShu Zhu, Hui Xiong, Qing He

In order to show the performance of different transfer learning models, over twenty representative transfer learning models are used for experiments.

Transfer Learning

Efficient and Adaptive Kernelization for Nonlinear Max-margin Multi-view Learning

no code implementations11 Oct 2019 Changying Du, Jia He, Changde Du, Fuzhen Zhuang, Qing He, Guoping Long

Existing multi-view learning methods based on kernel function either require the user to select and tune a single predefined kernel or have to compute and store many Gram matrices to perform multiple kernel learning.

Data Augmentation MULTI-VIEW LEARNING

Learning beyond Predefined Label Space via Bayesian Nonparametric Topic Modelling

no code implementations10 Oct 2019 Changying Du, Fuzhen Zhuang, Jia He, Qing He, Guoping Long

In real world machine learning applications, testing data may contain some meaningful new categories that have not been seen in labeled training data.

Unsupervised Neural Aspect Extraction with Sememes

no code implementations IJCAI 2019 Ling Luo, Xiang Ao, Yan Song, Jinyao Li, Xiaopeng Yang, Qing He, Dong Yu

Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts.

Aspect Extraction Aspect Term Extraction and Sentiment Classification +1

Field-aware Calibration: A Simple and Empirically Strong Method for Reliable Probabilistic Predictions

no code implementations26 May 2019 Feiyang Pan, Xiang Ao, Pingzhong Tang, Min Lu, Dapeng Liu, Lei Xiao, Qing He

It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also known as the issue of miscalibration.

BIG-bench Machine Learning Click-Through Rate Prediction

Atom Responding Machine for Dialog Generation

no code implementations14 May 2019 Ganbin Zhou, Ping Luo, Jingwu Chen, Fen Lin, Leyu Lin, Qing He

To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms.

Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings

1 code implementation25 Apr 2019 Feiyang Pan, Shuokai Li, Xiang Ao, Pingzhong Tang, Qing He

We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs.

Click-Through Rate Prediction Meta-Learning

Web Based Brain Volume Calculation for Magnetic Resonance Images

no code implementations21 Apr 2019 Kevin Karsch, Brian Grinstead, Qing He, Ye Duan

Brain volume calculations are crucial in modern medical research, especially in the study of neurodevelopmental disorders.

Policy Optimization with Model-based Explorations

no code implementations18 Nov 2018 Feiyang Pan, Qingpeng Cai, An-Xiang Zeng, Chun-Xiang Pan, Qing Da, Hua-Lin He, Qing He, Pingzhong Tang

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games.

Atari Games Decision Making +3

Knowledge Graph Embedding with Hierarchical Relation Structure

no code implementations EMNLP 2018 Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He

To this end, in this paper, we extend existing KGE models TransE, TransH and DistMult, to learn knowledge representations by leveraging the information from the HRS.

Information Retrieval Knowledge Base Completion +4

Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents

no code implementations22 Aug 2018 Ganbin Zhou, Rongyu Cao, Xiang Ao, Ping Luo, Fen Lin, Leyu Lin, Qing He

Additionally, a "low-level sharing, high-level splitting" structure of CNN is designed to handle the documents from different content domains.

Free-rider Episode Screening via Dual Partition Model

no code implementations19 May 2018 Xiang Ao, Yang Liu, Zhen Huang, Luo Zuo, Qing He

An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently.

Policy Gradients for Contextual Recommendations

no code implementations12 Feb 2018 Feiyang Pan, Qingpeng Cai, Pingzhong Tang, Fuzhen Zhuang, Qing He

We evaluate PGCR on toy datasets as well as a real-world dataset of personalized music recommendations.

Decision Making Multi-Armed Bandits +2

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

no code implementations30 Apr 2017 Ganbin Zhou, Ping Luo, Rongyu Cao, Yijun Xiao, Fen Lin, Bo Chen, Qing He

Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output.

Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.