no code implementations • CCL 2021 • Qian Chen, Xiaoying Gao, Suge Wang, Xin Guo
“知识图谱问题生成任务是从给定的知识图谱中生成与其相关的问题。目前, 知识图谱问题生成模型主要使用基于RNN或Transformer对知识图谱子图进行编码, 但这种方式丢失了显式的图结构化信息, 在解码器中忽视了局部信息对节点的重要性。本文提出迭代信息传递图编码器来编码子图, 获取子图显式的图结构化信息, 此外, 我们还使用滑动窗口注意力机制提高RNN解码器, 提升子图局部信息对节点的重要度。从WQ和PQ数据集上的实验结果看, 我们提出的模型比KTG模型在BLEU4指标上分别高出2. 16和15. 44, 证明了该模型的有效性。”
1 code implementation • 30 Mar 2022 • Jiaao Zhan, Qian Chen, Boxing Chen, Wen Wang, Yu Bai, Yang Gao
In this paper, we propose a novel and general approach to enhance the target dependency within the NAT decoder from two perspectives: decoder input and decoder self-attention.
1 code implementation • CVPR 2022 • Lei Zhu, Qi She, Qian Chen, Yunfei You, Boyu Wang, Yanye Lu
To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects.
no code implementations • 16 Feb 2022 • Yi Ren, Ming Lei, Zhiying Huang, Shiliang Zhang, Qian Chen, Zhijie Yan, Zhou Zhao
Specifically, we first introduce a word-level prosody encoder, which quantizes the low-frequency band of the speech and compresses prosody attributes in the latent prosody vector (LPV).
1 code implementation • 29 Dec 2021 • Lei Zhu, Qi She, Qian Chen, Xiangxi Meng, Mufeng Geng, Lujia Jin, Zhe Jiang, Bin Qiu, Yunfei You, Yibao Zhang, Qiushi Ren, Yanye Lu
In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively.
no code implementations • 17 Dec 2021 • Qian Chen, Haoxin Bai, Bingchen Che, Tianyun Zhao, Ce Zhang, Kaige Wang, Jintao Bai, Wei Zhao
To date, live-cell imaging at the nanometer scale remains challenging.
1 code implementation • Findings (ACL) 2022 • Linhan Zhang, Qian Chen, Wen Wang, Chong Deng, Shiliang Zhang, Bing Li, Wei Wang, Xin Cao
In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document.
1 code implementation • ICLR 2022 • Chao-Hong Tan, Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Zhen-Hua Ling
We propose a novel Pooling Network (PoNet) for token mixing in long sequences with linear complexity.
no code implementations • 9 Sep 2021 • Siqi Zheng, Shiliang Zhang, Weilong Huang, Qian Chen, Hongbin Suo, Ming Lei, Jinwei Feng, Zhijie Yan
We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling.
1 code implementation • 2 Aug 2021 • Zhen Li, Jing Tang, Deqing Zou, Qian Chen, Shouhuai Xu, Chao Zhang, Yichen Li, Hai Jin
Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.
no code implementations • 21 Jul 2021 • Mengcheng Lan, Shuliang Ning, Yanran Li, Qian Chen, Xunlai Chen, Xiaoguang Han, Shuguang Cui
Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with multi-prediction spaces.
no code implementations • 20 Jul 2021 • Qinglin Zhang, Qian Chen, YaLi Li, Jiaqing Liu, Wen Wang
Evaluations are conducted on the English Wiki-727K document segmentation benchmark, a Chinese Wikipedia-based document segmentation dataset we created, and an in-house Chinese spoken document dataset.
no code implementations • NeurIPS 2021 • Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Pan Zhou, Benjamin I. P. Rubinstein, Ce Zhang, Bo Li
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
1 code implementation • 28 Apr 2021 • Yi Zhang, Geng Chen, Qian Chen, Yujia Sun, Yong Xia, Olivier Deforges, Wassim Hamidouche, Lu Zhang
We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms.
no code implementations • 21 Apr 2021 • Qian Chen, Wen Wang, Mengzhe Chen, Qinglin Zhang
Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing applications.
no code implementations • 21 Apr 2021 • Qian Chen, Wen Wang, Qinglin Zhang
In this paper, we propose a novel joint textual-phonetic pre-training approach for learning spoken language representations, aiming at exploring the full potentials of phonetic information to improve SLU robustness to ASR errors.
Automatic Speech Recognition
Natural Language Understanding
+3
1 code implementation • NeurIPS 2021 • Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Benjamin Rubinstein, Pan Zhou, Ce Zhang, Bo Li
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
1 code implementation • 25 Jan 2021 • Qian Chen, Ze Liu, Yi Zhang, Keren Fu, Qijun Zhao, Hongwei Du
The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams.
no code implementations • 25 Nov 2020 • Qinyan Huang, Weiwen Zhou, Minjie Wan, Xin Chen, Qian Chen, Guohua Gu
Active contour model (ACM) is one of the most widely used image segmentation tools at present, but the existing methods only utilize the local or global single feature information of image to minimize the energy function, which is easy to cause false segmentations in IR images.
8 code implementations • 19 Nov 2020 • Xiao-Yang Liu, Hongyang Yang, Qian Chen, Runjia Zhang, Liuqing Yang, Bowen Xiao, Christina Dan Wang
In this paper, we introduce a DRL library FinRL that facilitates beginners to expose themselves to quantitative finance and to develop their own stock trading strategies.
1 code implementation • 4 Nov 2020 • Qian Chen, Keren Fu, Ze Liu, Geng Chen, Hongwei Du, Bensheng Qiu, LingShao
Finally, we propose an effective layer-wise aggregation module to fuse the features extracted from the enhanced depth maps and RGB images for the accurate detection of salient objects.
no code implementations • 11 Oct 2020 • Chao Ma, Guohua Gu, Xin Miao, Minjie Wan, Weixian Qian, Kan Ren, Qian Chen
Infrared target tracking plays an important role in both civil and military fields.
no code implementations • 3 Mar 2020 • Qian Chen, Zhu Zhuo, Wen Wang, Qiuyun Xu
We explore different transfer learning approaches to reduce dependency on data collection and annotation.
Spoken Language Understanding
Task-Oriented Dialogue Systems
+2
no code implementations • 3 Mar 2020 • Qian Chen, Mengzhe Chen, Bo Li, Wen Wang
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the performance of subsequent applications, such as machine translation, dialogue systems, and so forth.
1 code implementation • 3 Mar 2020 • Qian Chen, Wen Wang
The noetic end-to-end response selection challenge as one track in the 7th Dialog System Technology Challenges (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context.
1 code implementation • 1 Jan 2020 • Yuntao Du, Zhiwen Tan, Qian Chen, Xiaowen Zhang, Yirong Yao, Chongjun Wang
Recent experiments have shown that when the discriminator is provided with domain information in both domains and label information in the source domain, it is able to preserve the complex multimodal information and high semantic information in both domains.
Ranked #3 on
Domain Adaptation
on ImageCLEF-DA
1 code implementation • 31 Dec 2019 • Yuntao Du, Zhiwen Tan, Qian Chen, Yi Zhang, Chongjun Wang
In this paper, we propose a novel online transfer learning method which seeks to find a new feature representation, so that the marginal distribution and conditional distribution discrepancy can be online reduced simultaneously.
3 code implementations • EMNLP 2020 • Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li
In particular, we propose a tree-based autoencoder to embed the discrete text data into a continuous representation space, upon which we optimize the adversarial perturbation.
1 code implementation • 5 Nov 2019 • Zhuo Wang, Runlong Hu, Qian Chen, Pei Gao, Xiaowei Xu
Previous works use review network effects, i. e. the relationships among reviewers, reviews, and products, to detect fake reviews or review spammers, but ignore time effects, which are critical in characterizing group spamming.
no code implementations • 19 Aug 2019 • Zhi-Xiu Ye, Qian Chen, Wen Wang, Zhen-Hua Ling
We also observe that fine-tuned models after the proposed pre-training approach maintain comparable performance on other NLP tasks, such as sentence classification and natural language inference tasks, compared to the original BERT models.
Ranked #14 on
Common Sense Reasoning
on CommonsenseQA
no code implementations • 24 Jun 2019 • Yuan Yuan, Tracy Liu, Chenhao Tan, Qian Chen, Alex Pentland, Jie Tang
Using data on 36 million online red packet gifts on China's social site WeChat, we leverage a natural experimental design to identify the social contagion of gift giving in online groups.
1 code implementation • 27 Apr 2019 • Tianda Li, Xiaodan Zhu, Quan Liu, Qian Chen, Zhigang Chen, Si Wei
Natural language inference (NLI) is among the most challenging tasks in natural language understanding.
1 code implementation • 12 Apr 2019 • Jiaji Li, Alex Matlock, Yunzhe Li, Qian Chen, Chao Zuo, Lei Tian
We demonstrate a label-free, scan-free {\it intensity} diffraction tomography technique utilizing annular illumination (aIDT) to rapidly characterize large-volume 3D refractive index distributions in vitro.
Optics Biological Physics
14 code implementations • 28 Feb 2019 • Qian Chen, Zhu Zhuo, Wen Wang
Intent classification and slot filling are two essential tasks for natural language understanding.
Ranked #2 on
Slot Filling
on ATIS
4 code implementations • 9 Jan 2019 • Qian Chen, Wen Wang
The noetic end-to-end response selection challenge as one track in Dialog System Technology Challenges 7 (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context.
Ranked #1 on
Conversational Response Selection
on Advising Corpus
no code implementations • 12 Oct 2018 • Xiaodong Kuang, Xiubao Sui, Chengwei Liu, Yu-An Liu, Qian Chen, Guohua Gu
Transforming a thermal infrared image into a realistic RGB image is a challenging task.
no code implementations • 5 Jul 2018 • Chao Wang, Richard Gerlach, Qian Chen
One-day-ahead VaR and ES forecasting results favor the proposed models, especially when incorporating the sub-sampled Realized Variance and the sub-sampled Realized Range in the model.
1 code implementation • COLING 2018 • Qian Chen, Zhen-Hua Ling, Xiaodan Zhu
This paper explores generalized pooling methods to enhance sentence embedding.
Ranked #10 on
Sentiment Analysis
on Yelp Fine-grained classification
no code implementations • ICLR 2018 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen
Modeling informal inference in natural language is very challenging.
no code implementations • 15 Nov 2017 • Yu-Ping Ruan, Qian Chen, Zhen-Hua Ling
The description layer utilizes modified LSTM units to process these chunk-level vectors in a recurrent manner and produces sequential encoding outputs.
1 code implementation • ACL 2018 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen, Si Wei
With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance.
Ranked #18 on
Natural Language Inference
on SNLI
no code implementations • 15 Sep 2017 • Huidong Dai, Weiji He, Guohua Gu, Ling Ye, Tianyi Mao, Qian Chen
The proposed multi-resolution photon counting 3D imaging technique acquires a high-resolution 3D image from a coarse image and edges at successfully finer resolution sampled by Hadamard multiplexing along the wavelet trees.
2 code implementations • WS 2017 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task.
Ranked #68 on
Natural Language Inference
on SNLI
no code implementations • 31 May 2017 • Chao Zuo, Tianyang Tao, Shijie Feng, Lei Huang, Anand Asundi, Qian Chen
Recent advances in imaging sensors and digital light projection technology have facilitated a rapid progress in 3D optical sensing, enabling 3D surfaces of complex-shaped objects to be captured with improved resolution and accuracy.
no code implementations • 14 Mar 2017 • Junbei Zhang, Xiaodan Zhu, Qian Chen, Li-Rong Dai, Si Wei, Hui Jiang
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA).
Ranked #40 on
Question Answering
on SQuAD1.1 dev
1 code implementation • 26 Oct 2016 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang
Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences.
11 code implementations • ACL 2017 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen
Reasoning and inference are central to human and artificial intelligence.
Ranked #27 on
Natural Language Inference
on SNLI