1 code implementation • Findings (NAACL) 2022 • Huan Lin, Baosong Yang, Liang Yao, Dayiheng Liu, Haibo Zhang, Jun Xie, Min Zhang, Jinsong Su
Diverse NMT aims at generating multiple diverse yet faithful translations given a source sentence.
no code implementations • WMT (EMNLP) 2021 • Yimeng Chen, Chang Su, Yingtao Zhang, Yuxia Wang, Xiang Geng, Hao Yang, Shimin Tao, Guo Jiaxin, Wang Minghan, Min Zhang, Yujia Liu, ShuJian Huang
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task.
no code implementations • INLG (ACL) 2021 • Minghan Wang, Guo Jiaxin, Yuxia Wang, Yimeng Chen, Su Chang, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang
Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.
1 code implementation • CoNLL (EMNLP) 2021 • Yang Hou, Houquan Zhou, Zhenghua Li, Yu Zhang, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan
In the coarse labeling stage, the joint model outputs a bracketed tree, in which each node corresponds to one of four labels (i. e., phrase, subphrase, word, subword).
no code implementations • WMT (EMNLP) 2021 • Zhengzhe Yu, Daimeng Wei, Zongyao Li, Hengchao Shang, Xiaoyu Chen, Zhanglin Wu, Jiaxin Guo, Minghan Wang, Lizhi Lei, Min Zhang, Hao Yang, Ying Qin
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task.
no code implementations • WMT (EMNLP) 2021 • Zongyao Li, Daimeng Wei, Hengchao Shang, Xiaoyu Chen, Zhanglin Wu, Zhengzhe Yu, Jiaxin Guo, Minghan Wang, Lizhi Lei, Min Zhang, Hao Yang, Ying Qin
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task.
no code implementations • CCL 2021 • Mingyue Zhou, Chen Gong, Zhenghua Li, Min Zhang
“数据标注最重要的考虑因素是数据的质量和标注代价。我们调研发现自然语言处理领域的数据标注工作通常采用机标人校的标注方法以降低代价;同时, 很少有工作严格对比不同标注方法, 以探讨标注方法对标注质量和代价的影响。该文借助一个成熟的标注团队, 以依存句法数据标注为案例, 实验对比了机标人校、双人独立标注、及本文通过融合前两种方法所新提出的人机独立标注方法, 得到了一些初步的结论。”
1 code implementation • ACL 2022 • Nan Yu, Meishan Zhang, Guohong Fu, Min Zhang
Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i. e. element discourse unit (EDU). To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP). We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective, leading a 2. 1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
no code implementations • ACL 2022 • Dengji Guo, Zhengrui Ma, Min Zhang, Yang Feng
Regularization methods applying input perturbation have drawn considerable attention and have been frequently explored for NMT tasks in recent years.
no code implementations • SemEval (NAACL) 2022 • Yinglu Li, Min Zhang, Xiaosong Qiao, Minghan Wang
In order to verify whether our model could also perform better in subtask 2 (the regression subtask), the ranking score is transformed into classification labels by an up-sampling strategy.
no code implementations • SemEval (NAACL) 2022 • Xiaosong Qiao, Yinglu Li, Min Zhang, Minghan Wang, Hao Yang, Shimin Tao, Qin Ying
This paper describes the system for the identifying Plausible Clarifications of Implicit and Underspecified Phrases.
no code implementations • WMT (EMNLP) 2021 • Hao Yang, Zhanglin Wu, Zhengzhe Yu, Xiaoyu Chen, Daimeng Wei, Zongyao Li, Hengchao Shang, Minghan Wang, Jiaxin Guo, Lizhi Lei, Chuanfei Xu, Min Zhang, Ying Qin
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).
no code implementations • WMT (EMNLP) 2021 • Daimeng Wei, Zongyao Li, Zhanglin Wu, Zhengzhe Yu, Xiaoyu Chen, Hengchao Shang, Jiaxin Guo, Minghan Wang, Lizhi Lei, Min Zhang, Hao Yang, Ying Qin
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task.
no code implementations • MTSummit 2021 • Minghan Wang, Jiaxin Guo, Yimeng Chen, Chang Su, Min Zhang, Shimin Tao, Hao Yang
Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT.
no code implementations • Findings (EMNLP) 2021 • Ying Li, Meishan Zhang, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan
Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains.
1 code implementation • Findings (EMNLP) 2021 • Qingrong Xia, Zhenghua Li, Rui Wang, Min Zhang
In particular, one recent seq-to-seq work directly fine-tunes AMR graph sequences on the encoder-decoder pre-trained language model and achieves new state-of-the-art results, outperforming previous works by a large margin.
no code implementations • EMNLP 2021 • Xinglin Lyu, Junhui Li, ZhengXian Gong, Min Zhang
In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT.
no code implementations • EMNLP (BlackboxNLP) 2021 • Minghan Wang, Guo Jiaxin, Yuxia Wang, Yimeng Chen, Su Chang, Hengchao Shang, Min Zhang, Shimin Tao, Hao Yang
Length prediction is a special task in a series of NAT models where target length has to be determined before generation.
1 code implementation • EMNLP 2021 • Xincheng Ju, Dong Zhang, Rong Xiao, Junhui Li, Shoushan Li, Min Zhang, Guodong Zhou
Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA).
no code implementations • EMNLP 2020 • Lijie Wang, Ao Zhang, Kun Wu, Ke Sun, Zhenghua Li, Hua Wu, Min Zhang, Haifeng Wang
This paper describes in detail the construction process and data statistics of DuSQL.
no code implementations • IWSLT (ACL) 2022 • Minghan Wang, Jiaxin Guo, Xiaosong Qiao, Yuxia Wang, Daimeng Wei, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, Ying Qin
For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora.
no code implementations • IWSLT (ACL) 2022 • Minghan Wang, Jiaxin Guo, Yinglu Li, Xiaosong Qiao, Yuxia Wang, Zongyao Li, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, Ying Qin
The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track.
no code implementations • IWSLT (ACL) 2022 • Jiaxin Guo, Yinglu Li, Minghan Wang, Xiaosong Qiao, Yuxia Wang, Hengchao Shang, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, Ying Qin
The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022.
no code implementations • Findings (ACL) 2022 • Yuxia Wang, Minghan Wang, Yimeng Chen, Shimin Tao, Jiaxin Guo, Chang Su, Min Zhang, Hao Yang
Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity.
no code implementations • Findings (ACL) 2022 • Kehai Chen, Masao Utiyama, Eiichiro Sumita, Rui Wang, Min Zhang
Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner.
no code implementations • COLING 2022 • Zijie Lin, Bin Liang, Yunfei Long, Yixue Dang, Min Yang, Min Zhang, Ruifeng Xu
This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities.
1 code implementation • COLING 2022 • Nan Yu, Guohong Fu, Min Zhang
It is believed that speaker interactions are helpful for this task.
Ranked #2 on
Discourse Parsing
on STAC
1 code implementation • COLING 2022 • Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
no code implementations • ACL 2022 • Ying Li, Shuaike Li, Min Zhang
To address this issue, we for the first time apply a dynamic matching network on the shared-private model for semi-supervised cross-domain dependency parsing.
no code implementations • 30 Jan 2023 • Zhanglin Wu, Min Zhang, Ming Zhu, Yinglu Li, Ting Zhu, Hao Yang, Song Peng, Ying Qin
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation.
no code implementations • 27 Jan 2023 • Chulun Zhou, Yunlong Liang, Fandong Meng, Jie zhou, Jinan Xu, Hongji Wang, Min Zhang, Jinsong Su
To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues.
no code implementations • 27 Jan 2023 • Xingwu Guo, Ziwei Zhou, Yueling Zhang, Guy Katz, Min Zhang
The experimental results demonstrate our approach's effectiveness and efficiency in verifying DNNs' robustness against various occlusions, and its ability to generate counterexamples when these DNNs are not robust.
1 code implementation • 22 Dec 2022 • Zhaoxin Fan, Kaixing Yang, Min Zhang, Zhenbo Song, Hongyan Liu, Jun He
In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image.
no code implementations • 16 Dec 2022 • Qian Yang, Qian Chen, Wen Wang, Baotian Hu, Min Zhang
However, these methods fail to build connections between candidates and thus cannot model the inter-dependent relation during retrieval.
no code implementations • 12 Dec 2022 • Yachao Li, Junhui Li, Jing Jiang, Shimin Tao, Hao Yang, Min Zhang
To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention.
1 code implementation • 10 Dec 2022 • Yedi Zhang, Zhe Zhao, Fu Song, Min Zhang, Taolue Chen, Jun Sun
Experimental results on QNNs with different quantization bits confirm the effectiveness and efficiency of our approach, e. g., two orders of magnitude faster and able to solve more verification tasks in the same time limit than the state-of-the-art methods.
1 code implementation • 8 Dec 2022 • Zhaocong Li, Xuebo Liu, Derek F. Wong, Lidia S. Chao, Min Zhang
In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model.
1 code implementation • 2 Dec 2022 • Hexuan Deng, Liang Ding, Xuebo Liu, Meishan Zhang, DaCheng Tao, Min Zhang
Preliminary experiments on En-Zh and En-Ja news domain corpora demonstrate that monolingual data can significantly improve translation quality (e. g., +3. 15 BLEU on En-Zh).
1 code implementation • 23 Nov 2022 • Zhijun Wang, Xuebo Liu, Min Zhang
Existing research generally treats Chinese character as a minimum unit for representation.
Ranked #1 on
Machine Translation
on WMT2017 Chinese-English
no code implementations • 21 Nov 2022 • Jiaxu Tian, Dapeng Zhi, Si Liu, Peixin Wang, Guy Katz, Min Zhang
In this paper we propose a novel, tight and scalable reachability analysis approach for DRL systems.
no code implementations • 21 Nov 2022 • Yiting Wu, Zhaodi Zhang, Zhiyi Xue, Si Liu, Min Zhang
We observe that existing approaches only rely on overestimated domains, while the corresponding tight approximation may not necessarily be tight on its actual domain.
1 code implementation • 13 Nov 2022 • Binbin Xie, Xiangpeng Wei, Baosong Yang, Huan Lin, Jun Xie, Xiaoli Wang, Min Zhang, Jinsong Su
Keyphrase generation aims to automatically generate short phrases summarizing an input document.
1 code implementation • 8 Nov 2022 • Jinpeng Zhang, Chuanqi Dong, Xiangyu Duan, Yuqi Zhang, Min Zhang
Word alignment is to find translationally equivalent words between source and target sentences.
1 code implementation • 3 Nov 2022 • Peiyuan Gong, Xuebo Liu, Heyan Huang, Min Zhang
Pretraining-based (PT-based) automatic evaluation metrics (e. g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e. g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods.
no code implementations • 31 Oct 2022 • Lei Zhang, Shilin Zhou, Chen Gong, Zhenghua Li, Zhefeng Wang, Baoxing Huai, Min Zhang
Chinese word segmentation (CWS) models have achieved very high performance when the training data is sufficient and in-domain.
1 code implementation • 31 Oct 2022 • Zhaochen Su, Zecheng Tang, Xinyan Guan, Juntao Li, Lijun Wu, Min Zhang
Existing methods mainly perform continual training to mitigate such a misalignment.
1 code implementation • 27 Oct 2022 • Peijie Jiang, Dingkun Long, Yanzhao Zhang, Pengjun Xie, Meishan Zhang, Min Zhang
We apply BABERT for feature induction of Chinese sequence labeling tasks.
Ranked #1 on
Chinese Word Segmentation
on MSRA
Chinese Named Entity Recognition
Chinese Word Segmentation
+2
1 code implementation • 23 Oct 2022 • Panzhong Lu, Xin Zhang, Meishan Zhang, Min Zhang
First, we construct a dataset of phrase grounding with both noun phrases and pronouns to image regions.
1 code implementation • 22 Oct 2022 • Yue Zhang, Bo Zhang, Zhenghua Li, Zuyi Bao, Chen Li, Min Zhang
Then, we obtain parse trees of the source incorrect sentences by projecting trees of the target correct sentences.
1 code implementation • 20 Oct 2022 • Yu Zhao, Jianguo Wei, Zhichao Lin, Yueheng Sun, Meishan Zhang, Min Zhang
Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones.
1 code implementation • 19 Oct 2022 • Hongqiu Wu, Ruixue Ding, Hai Zhao, Boli Chen, Pengjun Xie, Fei Huang, Min Zhang
Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios.
1 code implementation • COLING 2022 • Dan Qiao, Chenchen Dai, Yuyang Ding, Juntao Li, Qiang Chen, Wenliang Chen, Min Zhang
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks.
no code implementations • 16 Sep 2022 • Min Zhang, Hongyao Tang, Jianye Hao, Yan Zheng
First, we propose a unified policy abstraction theory, containing three types of policy abstraction associated to policy features at different levels.
no code implementations • 26 Aug 2022 • Saihao Huang, Lijie Wang, Zhenghua Li, Zeyang Liu, Chenhui Dou, Fukang Yan, Xinyan Xiao, Hua Wu, Min Zhang
As the first session-level Chinese dataset, CHASE contains two separate parts, i. e., 2, 003 sessions manually constructed from scratch (CHASE-C), and 3, 456 sessions translated from English SParC (CHASE-T).
no code implementations • 21 Aug 2022 • Zhaodi Zhang, Yiting Wu, Si Liu, Jing Liu, Min Zhang
Considerable efforts have been devoted to finding the so-called tighter approximations to obtain more precise verification results.
1 code implementation • 17 Aug 2022 • Ziyi Ye, Xiaohui Xie, Yiqun Liu, Zhihong Wang, Xuesong Chen, Min Zhang, Shaoping Ma
We explore the effectiveness of BTA for satisfaction modeling in two popular information access scenarios, i. e., search and recommendation.
1 code implementation • 11 Aug 2022 • Jingtao Zhan, Qingyao Ai, Yiqun Liu, Jiaxin Mao, Xiaohui Xie, Min Zhang, Shaoping Ma
By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data.
no code implementations • 24 Jul 2022 • Min Zhang, Zhihong Pan, Xin Zhou, C. -C. Jay Kuo
Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible Neural Networks (INN).
1 code implementation • 23 Jul 2022 • Qian Yang, Yunxin Li, Baotian Hu, Lin Ma, Yuxing Ding, Min Zhang
CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr.
1 code implementation • 14 Jul 2022 • Min Zhang, Siteng Huang, Wenbin Li, Donglin Wang
To solve this problem, we present a plug-in Hierarchical Tree Structure-aware (HTS) method, which not only learns the relationship of FSL and pretext tasks, but more importantly, can adaptively select and aggregate feature representations generated by pretext tasks to maximize the performance of FSL tasks.
1 code implementation • 26 Jun 2022 • Chenyang Wang, Yuanqing Yu, Weizhi Ma, Min Zhang, Chong Chen, Yiqun Liu, Shaoping Ma
Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance.
no code implementations • 25 Jun 2022 • Hongqiu Wu, Ruixue Ding, Hai Zhao, Pengjun Xie, Fei Huang, Min Zhang
Deep neural models (e. g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness.
no code implementations • 23 Jun 2022 • Yanxiang Jiang, Min Zhang, Fu-Chun Zheng, Yan Chen, Mehdi Bennis, Xiaohu You
In this paper, cooperative edge caching problem is studied in fog radio access networks (F-RANs).
no code implementations • 17 Jun 2022 • Yu Zhao, Yunxin Li, Yuxiang Wu, Baotian Hu, Qingcai Chen, Xiaolong Wang, Yuxin Ding, Min Zhang
To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i. e., knowledge-aware dialogue graph encoder and recall-enhanced generator.
no code implementations • 8 Jun 2022 • Yifan Wang, Weizhi Ma, Min Zhang, Yiqun Liu, Shaoping Ma
First, we summarize fairness definitions in the recommendation and provide several views to classify fairness issues.
no code implementations • 1 Jun 2022 • Omri Isac, Clark Barrett, Min Zhang, Guy Katz
In this work, we present a novel mechanism for enhancing Simplex-based DNN verifiers with proof production capabilities: the generation of an easy-to-check witness of unsatisfiability, which attests to the absence of errors.
1 code implementation • NAACL 2022 • Yahui Liu, Haoping Yang, Chen Gong, Qingrong Xia, Zhenghua Li, Min Zhang
1) Based on a frame-free annotation methodology, we avoid writing complex frames for new predicates.
no code implementations • 25 Apr 2022 • Fuchuan Tong, Siqi Zheng, Min Zhang, Yafeng Chen, Hongbin Suo, Qingyang Hong, Lin Li
In this work, we present a GCN-based approach for semi-supervised learning.
1 code implementation • 25 Apr 2022 • Jingtao Zhan, Xiaohui Xie, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation.
1 code implementation • NAACL 2022 • Linzhi Wu, Pengjun Xie, Jie zhou, Meishan Zhang, Chunping Ma, Guangwei Xu, Min Zhang
Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually.
1 code implementation • NAACL 2022 • Yue Zhang, Zhenghua Li, Zuyi Bao, Jiacheng Li, Bo Zhang, Chen Li, Fei Huang, Min Zhang
This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7, 063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources.
1 code implementation • ACL 2022 • Xin Zhang, Guangwei Xu, Yueheng Sun, Meishan Zhang, Xiaobin Wang, Min Zhang
Recent works of opinion expression identification (OEI) rely heavily on the quality and scale of the manually-constructed training corpus, which could be extremely difficult to satisfy.
1 code implementation • 20 Apr 2022 • Yisheng Xiao, Lijun Wu, Junliang Guo, Juntao Li, Min Zhang, Tao Qin, Tie-Yan Liu
While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, auto-regressive (AR) generation.
no code implementations • 16 Apr 2022 • Zheng Zhang, Liang Ding, Dazhao Cheng, Xuebo Liu, Min Zhang, DaCheng Tao
Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks.
1 code implementation • 6 Apr 2022 • Zhumin Chu, Zhihong Wang, Yiqun Liu, Yingye Huang, Min Zhang, Shaoping Ma
25 search agents and 51 users are recruited for the field study that lasts about 45 days.
no code implementations • 5 Apr 2022 • Yangkun Li, Weizhi Ma, Chong Chen, Min Zhang, Yiqun Liu, Shaoping Ma, Yuekui Yang
Among various methods of coping with overfitting, dropout is one of the representative ways.
no code implementations • 28 Mar 2022 • Min Cao, Shiping Li, Juntao Li, Liqiang Nie, Min Zhang
On top of this, the efficiency-focused study on the ITR system is introduced as the third perspective.
1 code implementation • Findings (ACL) 2022 • Houquan Zhou, Yang Li, Zhenghua Li, Min Zhang
In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks.
1 code implementation • ACL 2022 • Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, Jingbo Zhu, Xuebo Liu, Min Zhang
Inspired by this, we design a new architecture, {\it ODE Transformer}, which is analogous to the Runge-Kutta method that is well motivated in ODE.
1 code implementation • Findings (ACL) 2022 • Yiming Zhang, Min Zhang, Sai Wu, Junbo Zhao
The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence.
Ranked #3 on
Aspect-Based Sentiment Analysis
on SemEval 2014 Task 4 Sub Task 2
(using extra training data)
no code implementations • ACL 2022 • Chulun Zhou, Fandong Meng, Jie zhou, Min Zhang, Hongji Wang, Jinsong Su
Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner.
1 code implementation • 18 Jan 2022 • Chong Chen, Fei Sun, Min Zhang, Bolin Ding
From the perspective of utility, if a system's utility is damaged by some bad data, the system needs to forget these data to regain utility.
1 code implementation • 22 Dec 2021 • Changxing Wu, Liuwen Cao, Yubin Ge, Yang Liu, Min Zhang, Jinsong Su
Then, we employ a label sequence decoder to output the predicted labels in a top-down manner, where the predicted higher-level labels are directly used to guide the label prediction at the current level.
no code implementations • 22 Dec 2021 • Zhengzhe Yu, Jiaxin Guo, Minghan Wang, Daimeng Wei, Hengchao Shang, Zongyao Li, Zhanglin Wu, Yuxia Wang, Yimeng Chen, Chang Su, Min Zhang, Lizhi Lei, Shimin Tao, Hao Yang
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18.
no code implementations • 22 Dec 2021 • Jiaxin Guo, Minghan Wang, Daimeng Wei, Hengchao Shang, Yuxia Wang, Zongyao Li, Zhengzhe Yu, Zhanglin Wu, Yimeng Chen, Chang Su, Min Zhang, Lizhi Lei, Shimin Tao, Hao Yang
An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the combination of raw data and distilled data.
no code implementations • EAMT 2022 • Minghan Wang, Jiaxin Guo, Yuxia Wang, Daimeng Wei, Hengchao Shang, Chang Su, Yimeng Chen, Yinglu Li, Min Zhang, Shimin Tao, Hao Yang
In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework.
no code implementations • 13 Dec 2021 • Shiping Li, Min Cao, Min Zhang
In this paper, we propose a semantic-aligned embedding method for text-based person search, in which the feature alignment across modalities is achieved by automatically learning the semantic-aligned visual features and textual features.
1 code implementation • 13 Dec 2021 • Chong Liu, Xiaoyang Liu, Rongqin Zheng, Lixin Zhang, Xiaobo Liang, Juntao Li, Lijun Wu, Min Zhang, Leyu Lin
Sequential recommendation methods play an important role in real-world recommender systems.
1 code implementation • 11 Dec 2021 • Tong Zhu, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Min Zhang
Most previous studies of document-level event extraction mainly focus on building argument chains in an autoregressive way, which achieves a certain success but is inefficient in both training and inference.
Ranked #3 on
Document-level Event Extraction
on ChFinAnn
no code implementations • 8 Dec 2021 • Pranav Kadam, Min Zhang, Jiahao Gu, Shan Liu, C. -C. Jay Kuo
GreenPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans.
1 code implementation • COLING 2022 • Shilin Zhou, Qingrong Xia, Zhenghua Li, Yu Zhang, Yu Hong, Min Zhang
Moreover, we propose a simple constrained Viterbi procedure to ensure the legality of the output graph according to the constraints of the SRL structure.
no code implementations • 27 Nov 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success.
1 code implementation • CVPR 2022 • Yifeng Xiong, Jiadong Lin, Min Zhang, John E. Hopcroft, Kun He
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security.
no code implementations • 14 Oct 2021 • Xuesong Chen, Ziyi Ye, Xiaohui Xie, Yiqun Liu, Weihang Su, Shuqi Zhu, Min Zhang, Shaoping Ma
While search technologies have evolved to be robust and ubiquitous, the fundamental interaction paradigm has remained relatively stable for decades.
1 code implementation • COLING 2022 • Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu, Min Zhang
Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community.
Ranked #1 on
Semantic Role Labeling
on OntoNotes
4 code implementations • 12 Oct 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space.
no code implementations • 29 Sep 2021 • Jiadong Lin, Yifeng Xiong, Min Zhang, John E. Hopcroft, Kun He
Black-box adversarial attack has attracted much attention for its practical use in deep learning applications, and it is very challenging as there is no access to the architecture and weights of the target model.
no code implementations • 29 Sep 2021 • Yue Wang, Lijun Wu, Xiaobo Liang, Juntao Li, Min Zhang
Starting from the resurgence of deep learning, language models (LMs) have never been so popular.
no code implementations • 29 Sep 2021 • Xiaobo Liang, Runze Mao, Lijun Wu, Juntao Li, Weiqing Liu, Qing Li, Min Zhang
The common approach of consistency training is performed on the data-level, which typically utilizes the data augmentation strategy (or adversarial training) to make the predictions from the augmented input and the original input to be consistent, so that the model is more robust and attains better generalization ability.
no code implementations • 24 Sep 2021 • Min Zhang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo
It is named GSIP (Green Segmentation of Indoor Point clouds) and its performance is evaluated on a representative large-scale benchmark -- the Stanford 3D Indoor Segmentation (S3DIS) dataset.
no code implementations • 22 Sep 2021 • Ziyi Ye, Xiaohui Xie, Yiqun Liu, Zhihong Wang, Xuancheng Li, Jiaji Li, Xuesong Chen, Min Zhang, Shaoping Ma
Inspired by these findings, we conduct supervised learning tasks to estimate the usefulness of non-click results with brain signals and conventional information (i. e., content and context factors).
no code implementations • 1 Sep 2021 • Xiaotian Jiang, Danshi Wang, Qirui Fan, Min Zhang, Chao Lu, Alan Pak Tao Lau
A physics-informed neural network (PINN) that combines deep learning with physics is studied to solve the nonlinear Schr\"odinger equation for learning nonlinear dynamics in fiber optics.
no code implementations • 9 Aug 2021 • Minghan Wang, Yuxia Wang, Chang Su, Jiaxin Guo, Yingtao Zhang, Yujia Liu, Min Zhang, Shimin Tao, Xingshan Zeng, Liangyou Li, Hao Yang, Ying Qin
This paper describes our work in participation of the IWSLT-2021 offline speech translation task.
1 code implementation • 3 Aug 2021 • Ziyi Ye, Xiaohui Xie, Yiqun Liu, Zhihong Wang, Xuesong Chen, Min Zhang, Shaoping Ma
In this paper, we carefully design a lab-based user study to investigate brain activities during reading comprehension.
5 code implementations • 2 Aug 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size.
no code implementations • ACL 2021 • Linqing Chen, Junhui Li, ZhengXian Gong, Boxing Chen, Weihua Luo, Min Zhang, Guodong Zhou
To this end, we propose two pre-training tasks.
no code implementations • ACL 2021 • Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou
We hope that knowledge gained while learning for English AMR parsing and text generation can be transferred to the counterparts of other languages.
1 code implementation • Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 2021 • An-Hui Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, Jinsong Su
Conversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation.
Ranked #3 on
Discourse Parsing
on STAC
no code implementations • 16 Jul 2021 • Pengju Zhang, Yonghui Jia, Muhua Zhu, Wenliang Chen, Min Zhang
Previous works for encoding questions mainly focus on the word sequences, but seldom consider the information from syntactic trees. In this paper, we propose an approach to learn syntax-based representations for KBQA.
9 code implementations • NeurIPS 2021 • Xiaobo Liang, Lijun Wu, Juntao Li, Yue Wang, Qi Meng, Tao Qin, Wei Chen, Min Zhang, Tie-Yan Liu
Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
Ranked #4 on
Machine Translation
on WMT2014 English-French
no code implementations • 13 Jun 2021 • Peng Jin, Min Zhang, Jianwen Li, Li Han, Xuejun Wen
Formally verifying Deep Reinforcement Learning (DRL) systems is a challenging task due to the dynamic continuity of system behaviors and the black-box feature of embedded neural networks.
1 code implementation • 11 Jun 2021 • Bin Hao, Min Zhang, Weizhi Ma, Shaoyun Shi, Xinxing Yu, Houzhi Shan, Yiqun Liu, Shaoping Ma
To the best of our knowledge, this is the largest real-world interaction dataset for personalized recommendation.
no code implementations • ACL 2021 • Xin Liu, Baosong Yang, Dayiheng Liu, Haibo Zhang, Weihua Luo, Min Zhang, Haiying Zhang, Jinsong Su
A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary.
1 code implementation • Findings (ACL) 2021 • Jinpeng Zhang, Baijun Ji, Nini Xiao, Xiangyu Duan, Min Zhang, Yangbin Shi, Weihua Luo
Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another, and is typically through learning linear projections to align monolingual word representation spaces.
1 code implementation • NAACL 2021 • Qingrong Xia, Bo Zhang, Rui Wang, Zhenghua Li, Yue Zhang, Fei Huang, Luo Si, Min Zhang
Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of {``}Who expressed what opinions towards what{''} in one sentence.
1 code implementation • ACL 2021 • Chen Gong, Saihao Huang, Houquan Zhou, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan
Several previous works on syntactic parsing propose to annotate shallow word-internal structures for better utilizing character-level information.
4 code implementations • 16 Apr 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance.
no code implementations • NeurIPS 2021 • Hongqiu Wu, Hai Zhao, Min Zhang
Beyond the success story of pre-trained language models (PrLMs) in recent natural language processing, they are susceptible to over-fitting due to unusual large model size.
no code implementations • 17 Mar 2021 • Juntao Li, Chang Liu, Chongyang Tao, Zhangming Chan, Dongyan Zhao, Min Zhang, Rui Yan
To fill the gap between these up-to-date methods and the real-world applications, we incorporate user-specific dialogue history into the response selection and propose a personalized hybrid matching network (PHMN).
1 code implementation • 15 Mar 2021 • Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo
Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work.
1 code implementation • EMNLP 2021 • Kun Wu, Lijie Wang, Zhenghua Li, Ao Zhang, Xinyan Xiao, Hua Wu, Min Zhang, Haifeng Wang
For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries.
no code implementations • ICCV 2021 • Min Zhang, Yang Guo, Na lei, Zhou Zhao, Jianfeng Wu, Xiaoyin Xu, Yalin Wang, Xianfeng GU
Shape analysis has been playing an important role in early diagnosis and prognosis of neurodegenerative diseases such as Alzheimer's diseases (AD).
1 code implementation • Findings (ACL) 2021 • Hongqiu Wu, Hai Zhao, Min Zhang
Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for programming language in the format of source code, serving in the most convenience of programmer developing.
5 code implementations • ACL 2021 • Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents.
Ranked #1 on
Key information extraction
on SROIE
no code implementations • 24 Dec 2020 • Yunqiu Shao, Bulou Liu, Jiaxin Mao, Yiqun Liu, Min Zhang, Shaoping Ma
We participated in the two case law tasks, i. e., the legal case retrieval task and the legal case entailment task.
no code implementations • COLING 2020 • Chen Gong, Zhenghua Li, Bowei Zou, Min Zhang
Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1. 12 and 5. 97 on NEWS and BAIKE data in F1.
no code implementations • COLING 2020 • Ying Li, Zhenghua Li, Min Zhang
The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training data when there is only a small-scale out-domain labeled data.
no code implementations • COLING 2020 • Huibin Ruan, Yu Hong, Yang Xu, Zhen Huang, Guodong Zhou, Min Zhang
We tackle implicit discourse relation recognition.
1 code implementation • COLING 2020 • Junjie Yu, Tong Zhu, Wenliang Chen, Wei zhang, Min Zhang
In this paper, we propose an alternative approach to improve RE systems via enriching diverse expressions by relational paraphrase sentences.
1 code implementation • COLING 2020 • Qingrong Xia, Rui Wang, Zhenghua Li, Yue Zhang, Min Zhang
Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention.
no code implementations • Findings of the Association for Computational Linguistics 2020 • WeiSheng Zhang, Kaisong Song, Yangyang Kang, Zhongqing Wang, Changlong Sun, Xiaozhong Liu, Shoushan Li, Min Zhang, Luo Si
As an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information.
1 code implementation • COLING 2020 • Tong Zhu, Haitao Wang, Junjie Yu, Xiabing Zhou, Wenliang Chen, Wei zhang, Min Zhang
The experimental results show that the ranking lists of the comparison systems on the DS-labelled test data and human-annotated test data are different.
1 code implementation • 30 Oct 2020 • Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Qi Tian, Min Zhang
Concretely, we design a novel interpretation scheme whereby the loss of mis-predicted frequent and sparse answers of the same question type is distinctly exhibited during the late training phase.
1 code implementation • COLING 2020 • Huaao Zhang, Shigui Qiu, Xiangyu Duan, Min Zhang
Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs.
2 code implementations • 20 Oct 2020 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, Shaoping Ma
Through this process, it teaches the DR model how to retrieve relevant documents from the entire corpus instead of how to rerank a potentially biased sample of documents.
no code implementations • 17 Oct 2020 • Min Zhang, Yao Shu, Kun He
Finite-sum optimization plays an important role in the area of machine learning, and hence has triggered a surge of interest in recent years.
1 code implementation • EMNLP 2020 • Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou
In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance.
Ranked #11 on
AMR Parsing
on LDC2017T10
(using extra training data)
1 code implementation • 1 Oct 2020 • Ding-Nan Zo, Song-Hai Zhang, Tai-Jiang M, Min Zhang
It is currently the largest dataset for fine-grained classification of dogs, including130 dog breeds and 70, 428 real-world images.
1 code implementation • 10 Sep 2020 • Siteng Huang, Min Zhang, Yachen Kang, Donglin Wang
However, these approaches only augment the representations of samples with available semantics while ignoring the query set, which loses the potential for the improvement and may lead to a shift between the modalities combination and the pure-visual representation.
no code implementations • 2 Sep 2020 • Pranav Kadam, Min Zhang, Shan Liu, C. -C. Jay Kuo
An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work.
no code implementations • 2 Sep 2020 • Min Zhang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo
The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner through a cascaded encoder-decoder architecture.
3 code implementations • 20 Aug 2020 • Shaoyun Shi, Hanxiong Chen, Weizhi Ma, Jiaxin Mao, Min Zhang, Yongfeng Zhang
Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs.
no code implementations • 16 Jul 2020 • Wenjie Wan, Zhaodi Zhang, Yiwei Zhu, Min Zhang, Fu Song
The key insight of our approach is that the robustness verification problem of DNNs can be solved by verifying sub-problems of DNNs, one per target label.
1 code implementation • 12 Jul 2020 • Feiyu Yang, Zhan Song, Zhenzhong Xiao, Yu Chen, Zhe Pan, Min Zhang, Min Xue, Yaoyang Mo, Yao Zhang, Guoxiong Guan, Beibei Qian
Recently, the leading performance of human pose estimation is dominated by heatmap based methods.
1 code implementation • ACL 2020 • Xiangyu Duan, Baijun Ji, Hao Jia, Min Tan, Min Zhang, Boxing Chen, Weihua Luo, Yue Zhang
In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary.
no code implementations • ACL 2020 • Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang
The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9. 29 over the syntax-agnostic baseline.
2 code implementations • 1 Jul 2020 • Chong Chen, Min Zhang, Weizhi Ma, Yiqun Liu, and Shaoping Ma
However, existing KG enhanced recommendation methods have largely focused on exploring advanced neural network architectures to better investigate the structural information of KG.
no code implementations • ACL 2020 • Xiao Chen, Changlong Sun, Jingjing Wang, Shoushan Li, Luo Si, Min Zhang, Guodong Zhou
This justifies the importance of the document-level sentiment preference information to ASC and the effectiveness of our approach capturing such information.
3 code implementations • 28 Jun 2020 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, Shaoping Ma
Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized embeddings.
2 code implementations • WWW 2020 • Chong Chen, Min Zhang, Weizhi Ma, Yiqun Liu, and Shaoping Ma Department of Computer Science and Technology, Institute for Articial Intelligence, Beijing National Research Center for Information Science and Technology, Tsinghua University cc17@mails.tsinghua.edu.cn, z-m@tsinghua.edu.cn
Factorization Machines (FM) with negative sampling is a popular solution for context-aware recommendation.
2 code implementations • ACL 2020 • Yu Zhang, Zhenghua Li, Min Zhang
Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data.
Ranked #1 on
Dependency Parsing
on CoNLL-2009
no code implementations • 1 Apr 2020 • Jinshan Zeng, Min Zhang, Shao-Bo Lin
Boosting is a well-known method for improving the accuracy of weak learners in machine learning.
1 code implementation • 6 Mar 2020 • Houquan Zhou, Yu Zhang, Zhenghua Li, Min Zhang
In the pre deep learning era, part-of-speech tags have been considered as indispensable ingredients for feature engineering in dependency parsing.
2 code implementations • 9 Feb 2020 • Min Zhang, Yifan Wang, Pranav Kadam, Shan Liu, C. -C. Jay Kuo
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.
no code implementations • 22 Jan 2020 • Kun He, Min Zhang, Jianrong Zhou, Yan Jin, Chu-min Li
Inspired by its success in deep learning, we apply the idea of SGD with batch selection of samples to a classic optimization problem in decision version.
no code implementations • ECCV 2020 • Dongsheng An, Yang Guo, Min Zhang, Xin Qi, Na lei, Shing-Tung Yau, Xianfeng GU
Though generative adversarial networks (GANs) areprominent models to generate realistic and crisp images, they often encounter the mode collapse problems and arehard to train, which comes from approximating the intrinsicdiscontinuous distribution transform map with continuousDNNs.