no code implementations • Findings (EMNLP) 2021 • Feiteng Mu, Wenjie Li, Zhipeng Xie
Given an input cause sentence, a causal subgraph is retrieved from the event causality network and is encoded with the graph attention mechanism, in order to support better reasoning of the potential effects.
1 code implementation • ACL 2022 • Yongqi Li, Wenjie Li, Liqiang Nie
In this paper, we hence define a novel research task, i. e., multimodal conversational question answering (MMCoQA), aiming to answer users’ questions with multimodal knowledge sources via multi-turn conversations.
no code implementations • EMNLP 2021 • Ruifeng Yuan, Zili Wang, Wenjie Li
Sentence fusion is a conditional generation task that merges several related sentences into a coherent one, which can be deemed as a summary sentence.
no code implementations • 31 May 2022 • Wenjie Li, Qiaolin Xia, Junfeng Deng, Hao Cheng, Jiangming Liu, Kouying Xue, Yong Cheng, Shu-Tao Xia
As an emerging secure learning paradigm in leveraging cross-agency private data, vertical federated learning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher.
no code implementations • 30 May 2022 • Wenjie Li, Qifan Song, Jean Honorio, Guang Lin
This work establishes the first framework of federated $\mathcal{X}$-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figure out the global optimum.
no code implementations • 23 May 2022 • Wei Wang, Xin Zhang, Jiaqi Yi, Xianqi Liao, Wenjie Li, Zhenhong Li
The experimental results show that the image denoising method of ZrO2 ceramic bearing ball surface defect based on cartoon-texture decomposition model can denoise while retaining the image details.
1 code implementation • 29 Apr 2022 • Wenge Liu, Yi Cheng, Hao Wang, Jianheng Tang, Yafei Liu, Ruihui Zhao, Wenjie Li, Yefeng Zheng, Xiaodan Liang
In this paper, we explore how to bring interpretability to data-driven DSMD.
1 code implementation • 28 Apr 2022 • Guangwei Gao, Zhengxue Wang, Juncheng Li, Wenjie Li, Yi Yu, Tieyong Zeng
Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning.
no code implementations • 27 Feb 2022 • Chi-Hua Wang, Wenjie Li, Guang Cheng, Guang Lin
This paper presents a novel federated linear contextual bandits model, where individual clients face different K-armed stochastic bandits with high-dimensional decision context and coupled through common global parameters.
1 code implementation • 16 Dec 2021 • Guangwei Gao, Wenjie Li, Juncheng Li, Fei Wu, Huimin Lu, Yi Yu
Convolutional neural networks based single-image super-resolution (SISR) has made great progress in recent years.
1 code implementation • CVPR 2022 • Haisong Liu, Tao Lu, Yihui Xu, Jia Liu, Wenjie Li, Lijun Chen
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data.
no code implementations • 9 Oct 2021 • Jiashuo Wang, Wenjie Li, Peiqin Lin, Feiteng Mu
Empathetic response generation aims to comprehend the user emotion and then respond to it appropriately.
no code implementations • 29 Sep 2021 • Naiqi Li, Wenjie Li, Yong Jiang, Shu-Tao Xia
In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning.
1 code implementation • 26 Aug 2021 • Shichao Sun, Wenjie Li
During the training stage, with teacher forcing these models are optimized to maximize the likelihood of the gold summary given the gold summary tokens as input to the decoder, while at inference the given tokens are replaced by the generated tokens.
no code implementations • SEMEVAL 2021 • Rong Xiang, Jinghang Gu, Emmanuele Chersoni, Wenjie Li, Qin Lu, Chu-Ren Huang
In this contribution, we describe the system presented by the PolyU CBS-Comp Team at the Task 1 of SemEval 2021, where the goal was the estimation of the complexity of words in a given sentence context.
no code implementations • 17 Jun 2021 • Wenjie Li, Chi-Hua Wang, Qifan Song, Guang Cheng
In this paper, we make the key delineation on the roles of resolution and statistical uncertainty in hierarchical bandits-based black-box optimization algorithms, guiding a more general analysis and a more efficient algorithm design.
no code implementations • 17 Apr 2021 • Yongqi Li, Wenjie Li
In this paper, we study a related but orthogonal issue, data distillation, which aims to distill the knowledge from a large training dataset down to a smaller and synthetic one.
no code implementations • 17 Apr 2021 • Yongqi Li, Wenjie Li, Liqiang Nie
Moreover, in order to collect more complementary information in the historical context, we also propose to incorporate the multi-round relevance feedback technique to explore the impact of the retrieval context on current question understanding.
Conversational Question Answering
Open-Domain Question Answering
no code implementations • 18 Feb 2021 • Wenjie Li, Adarsh Barik, Jean Honorio
Stochastic high dimensional bandit problems with low dimensional structures are useful in different applications such as online advertising and drug discovery.
no code implementations • 18 Jan 2021 • Yongqi Li, Wenjie Li, Liqiang Nie
In the past years, Knowledge-Based Question Answering (KBQA), which aims to answer natural language questions using facts in a knowledge base, has been well developed.
no code implementations • 1 Jan 2021 • Wenjie Li, Guang Cheng
Numerous adaptive algorithms such as AMSGrad and Radam have been proposed and applied to deep learning recently.
no code implementations • 26 Dec 2020 • Wenjie Li, Zhanyu Wang, Yichen Zhang, Guang Cheng
In this work, we investigate the idea of variance reduction by studying its properties with general adaptive mirror descent algorithms in nonsmooth nonconvex finite-sum optimization problems.
1 code implementation • NeurIPS 2020 • Naiqi Li, Wenjie Li, Jifeng Sun, Yinghua Gao, Yong Jiang, Shu-Tao Xia
In this paper we propose Stochastic Deep Gaussian Processes over Graphs (DGPG), which are deep structure models that learn the mappings between input and output signals in graph domains.
1 code implementation • COLING 2020 • Ruifeng Yuan, Zili Wang, Wenjie Li
We also introduce a hierarchical structure, which incorporates the multi-level of granularities of the textual information into the model.
no code implementations • 19 May 2020 • Wenjie Li, Benlai Tang, Xiang Yin, Yushi Zhao, Wei Li, Kang Wang, Hao Huang, Yuxuan Wang, Zejun Ma
Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre.
no code implementations • 12 May 2020 • Wenjie Li, Benedetta Tondi, Rongrong Ni, Mauro Barni
Transferability of adversarial examples is a key issue to apply this kind of attacks against multimedia forensics (MMF) techniques based on Deep Learning (DL) in a real-life setting.
1 code implementation • 21 Apr 2020 • Wenjie Li, Zhaoyang Zhang, Xinjiang Wang, Ping Luo
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's fast convergence would possibly lead the algorithm to local minimums.
no code implementations • 30 Jan 2020 • Sheng Zhou, Xinjiang Wang, Ping Luo, Litong Feng, Wenjie Li, Wei zhang
This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.
no code implementations • ACL 2019 • Hai Ye, Wenjie Li, Lu Wang
Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL description for some given MRs.
5 code implementations • 11 May 2019 • Hongwei Wang, Fuzheng Zhang, Mengdi Zhang, Jure Leskovec, Miao Zhao, Wenjie Li, Zhongyuan Wang
Here we propose Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) to provide better recommendations.
Ranked #1 on
Recommendation Systems
on Dianping-Food
8 code implementations • 18 Mar 2019 • Hongwei Wang, Miao Zhao, Xing Xie, Wenjie Li, Minyi Guo
To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information.
Ranked #1 on
Click-Through Rate Prediction
on Book-Crossing
no code implementations • 2 Feb 2019 • Yu Lei, Wenjie Li
In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations.
4 code implementations • 23 Jan 2019 • Hongwei Wang, Fuzheng Zhang, Miao Zhao, Wenjie Li, Xing Xie, Minyi Guo
Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems.
no code implementations • 19 Nov 2018 • Chenchen Li, Jialin Wang, Hongwei Wang, Miao Zhao, Wenjie Li, Xiaotie Deng
To enhance the emotion discriminativeness of words in textual feature extraction, we propose Emotional Word Embedding (EWE) to learn text representations by jointly considering their semantics and emotions.
no code implementations • 9 Nov 2018 • Yan-ran Li, Wenjie Li, Ziqiang Cao, Chengyao Chen
To sustain engaging conversation, it is critical for chatbots to make good use of relevant knowledge.
no code implementations • 2 Nov 2018 • Yan-ran Li, Wenjie Li
We propose a chatbot, namely Mocha to make good use of relevant entities when generating responses.
no code implementations • EMNLP 2018 • Jiachen Du, Wenjie Li, Yulan He, Ruifeng Xu, Lidong Bing, Xuan Wang
Combining the virtues of probability graphic models and neural networks, Conditional Variational Auto-encoder (CVAE) has shown promising performance in applications such as response generation.
no code implementations • EMNLP 2018 • Hui Su, Xiaoyu Shen, Wenjie Li, Dietrich Klakow
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems.
no code implementations • ACL 2018 • Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei
Most previous seq2seq summarization systems purely depend on the source text to generate summaries, which tends to work unstably.
Ranked #19 on
Text Summarization
on GigaWord
no code implementations • 7 Jun 2018 • Qizhi Zhang, Kuang-Chih Lee, Hongying Bao, Yuan You, Wenjie Li, Dongbai Guo
Therefore, it is infeasible to solve the multi-class classification problem using deep neural network when the number of classes are huge.
1 code implementation • ACL 2018 • Jingjing Xu, Xu sun, Qi Zeng, Xuancheng Ren, Xiaodong Zhang, Houfeng Wang, Wenjie Li
We evaluate our approach on two review datasets, Yelp and Amazon.
Ranked #5 on
Unsupervised Text Style Transfer
on Yelp
10 code implementations • 9 Mar 2018 • Hongwei Wang, Fuzheng Zhang, Jialin Wang, Miao Zhao, Wenjie Li, Xing Xie, Minyi Guo
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance.
Ranked #2 on
Click-Through Rate Prediction
on Book-Crossing
1 code implementation • NAACL 2018 • Shuming Ma, Xu sun, Wei Li, Sujian Li, Wenjie Li, Xuancheng Ren
The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words.
no code implementations • 25 Nov 2017 • Xu Sun, Weiwei Sun, Shuming Ma, Xuancheng Ren, Yi Zhang, Wenjie Li, Houfeng Wang
The decoding of the complex structure model is regularized by the additionally trained simple structure model.
no code implementations • 13 Nov 2017 • Ziqiang Cao, Furu Wei, Wenjie Li, Sujian Li
While previous abstractive summarization approaches usually focus on the improvement of informativeness, we argue that faithfulness is also a vital prerequisite for a practical abstractive summarization system.
Ranked #18 on
Text Summarization
on GigaWord
13 code implementations • IJCNLP 2017 • Yan-ran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, Shuzi Niu
We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects.
no code implementations • ACL 2017 • Jianbo Ye, Yan-ran Li, Zhaohui Wu, James Z. Wang, Wenjie Li, Jia Li
The new clustering method is easy to use and consistently outperforms other methods on a variety of data sets.
1 code implementation • ACL 2017 • Shuming Ma, Xu sun, Jingjing Xu, Houfeng Wang, Wenjie Li, Qi Su
In this work, our goal is to improve semantic relevance between source texts and summaries for Chinese social media summarization.
no code implementations • ACL 2017 • Xiaoyu Shen, Hui Su, Yan-ran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.
no code implementations • 26 Feb 2017 • Tong Che, Yan-ran Li, Ruixiang Zhang, R. Devon Hjelm, Wenjie Li, Yangqiu Song, Yoshua Bengio
Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted.
no code implementations • 7 Dec 2016 • Tong Che, Yan-ran Li, Athul Paul Jacob, Yoshua Bengio, Wenjie Li
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes.
no code implementations • COLING 2016 • Chengyao Chen, Zhitao Wang, Yu Lei, Wenjie Li
The advantages of the proposed model is the ability to handle the semantic information and to learn two influence components including the opinion influence of the content information and the social relation factors.
no code implementations • 28 Nov 2016 • Ziqiang Cao, Chuwei Luo, Wenjie Li, Sujian Li
In this paper, we develop a novel Seq2Seq model to fuse a copying decoder and a restricted generative decoder.
no code implementations • 28 Nov 2016 • Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents.
no code implementations • LREC 2016 • Minglei Li, Yunfei Long, Lu Qin, Wenjie Li
Secondly, a SVM based classifier is used to select the data whose natural labels are consistent with the predicted labels.
no code implementations • COLING 2016 • Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei, Yan-ran Li
Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization.
no code implementations • 26 Nov 2015 • Ziqiang Cao, Chengyao Chen, Wenjie Li, Sujian Li, Furu Wei, Ming Zhou
Both informativeness and readability of the collected summaries are verified by manual judgment.
no code implementations • EMNLP 2015 • Yan-ran Li, Wenjie Li, Fei Sun, Sujian Li
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English.
no code implementations • 5 Feb 2015 • Xiaozhao Zhao, Yuexian Hou, Dawei Song, Wenjie Li
We then revisit Boltzmann machines (BM) from a model selection perspective and theoretically show that both the fully visible BM (VBM) and the BM with hidden units can be derived from the general binary multivariate distribution using the CIF principle.
no code implementations • 16 Feb 2013 • Xiaozhao Zhao, Yuexian Hou, Qian Yu, Dawei Song, Wenjie Li
Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data.