Search Results for author: Min Zhang

Found 250 papers, 94 papers with code

HI-CMLM: Improve CMLM with Hybrid Decoder Input

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.

NMT Translation

A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing

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).

Part-Of-Speech Tagging POS +1

数据标注方法比较研究:以依存句法树标注为例(Comparison Study on Data Annotation Approaches: Dependency Tree Annotation as Case Study)

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。”

RST Discourse Parsing with Second-Stage EDU-Level Pre-training

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.

Discourse Marker Prediction Discourse Parsing

Prediction Difference Regularization against Perturbation for Neural Machine Translation

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.

Machine Translation NMT +1

HW-TSC at SemEval-2022 Task 3: A Unified Approach Fine-tuned on Multilingual Pretrained Model for PreTENS

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.


HW-TSC’s Submissions to the WMT21 Biomedical Translation Task

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).


Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation

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.

Multimodal Machine Translation NMT +2

APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing

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.

Dependency Parsing Language Modelling +1

Stacked AMR Parsing with Silver Data

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.

AMR Parsing Language Modelling

Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation

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.

Machine Translation NMT +1

Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection

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).

Sentiment Analysis

Synchronous Refinement for Neural Machine Translation

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.

Machine Translation Translation

Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training

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.

Machine Translation NMT +1

Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network

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.

Dependency Parsing Domain Adaptation

A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation

no code implementations27 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.

NMT Translation

OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks

no code implementations27 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.

SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation

1 code implementation22 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.

Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation

no code implementations16 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.

Answer Generation Language Modelling +3

P-Transformer: Towards Better Document-to-Document Neural Machine Translation

no code implementations12 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.

Machine Translation NMT +1

QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks

1 code implementation10 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.


ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation

1 code implementation8 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.

Low-Resource Neural Machine Translation NMT +2

Improving Simultaneous Machine Translation with Monolingual Data

1 code implementation2 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).

Knowledge Distillation Machine Translation +2

DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation

no code implementations21 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.

WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation

1 code implementation13 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.

Keyphrase Generation

Third-Party Aligner for Neural Word Alignments

1 code implementation8 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.

Language Modelling Word Alignment

Revisiting Grammatical Error Correction Evaluation and Beyond

1 code implementation3 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.

Grammatical Error Correction Machine Translation +1

Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data

no code implementations31 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.

Chinese Word Segmentation

Extending Phrase Grounding with Pronouns in Visual Dialogues

1 code implementation23 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.

Phrase Grounding

Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation

1 code implementation20 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.

Image Captioning Text Generation

Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning

1 code implementation19 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.

Language Modelling Meta-Learning

SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training

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.

text-classification Text Classification

Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes

no code implementations16 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.

Decision Making Metric Learning +2

SeSQL: Yet Another Large-scale Session-level Chinese Text-to-SQL Dataset

no code implementations26 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).

SQL Parsing Text-To-Sql

Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks

no code implementations21 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.

Brain Topography Adaptive Network for Satisfaction Modeling in Interactive Information Access System

1 code implementation17 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.

EEG Recommendation Systems +1

Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval

1 code implementation11 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.

Ad-Hoc Information Retrieval Domain Adaptation +1

Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network

no code implementations24 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).

Image Restoration Image Super-Resolution

Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation

1 code implementation14 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.

Few-Shot Image Classification

Towards Representation Alignment and Uniformity in Collaborative Filtering

1 code implementation26 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.

Collaborative Filtering Recommendation Systems

Adversarial Self-Attention for Language Understanding

no code implementations25 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.

Medical Dialogue Response Generation with Pivotal Information Recalling

no code implementations17 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.

Dialogue Generation Graph Attention +2

A Survey on the Fairness of Recommender Systems

no code implementations8 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.

Fairness Recommendation Systems

Neural Network Verification with Proof Production

no code implementations1 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.

Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models

1 code implementation25 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.


Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting

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.

named-entity-recognition NER

MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction

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.

Grammatical Error Correction Pretrained Language Models

Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations

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.

A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond

1 code implementation20 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.

Automatic Speech Recognition Dialogue Generation +7

BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation

no code implementations16 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.

Grammatical Error Correction Machine Translation +1

A Survey on Dropout Methods and Experimental Verification in Recommendation

no code implementations5 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.

Image-text Retrieval: A Survey on Recent Research and Development

no code implementations28 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.

Retrieval Text Retrieval

Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

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.


Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis

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.

Aspect-Based Sentiment Analysis Multi-Task Learning +1

Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation

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.

Knowledge Distillation Language Modelling +3

Recommendation Unlearning

1 code implementation18 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.

Recommendation Systems

A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition

1 code implementation22 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.

Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models

no code implementations22 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.

Machine Translation NMT +1

Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation

no code implementations22 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.

Knowledge Distillation Machine Translation +1

Learning Semantic-Aligned Feature Representation for Text-based Person Search

no code implementations13 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.

Person Search Text based Person Search

Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph

1 code implementation11 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.

Document-level Event Extraction Event Extraction

GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method

no code implementations8 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.

Visual Odometry

Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing

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.

Chinese Word Segmentation named-entity-recognition +2

Interpreting Dense Retrieval as Mixture of Topics

no code implementations27 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.


Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability

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.

Adversarial Attack

Web Search via an Efficient and Effective Brain-Machine Interface

no code implementations14 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.


Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval

4 code implementations12 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.

Information Retrieval Open-Domain Question Answering +2

Stochastic Variance Reduced Ensemble Adversarial Attack

no code implementations29 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.

Adversarial Attack

Are BERT Families Zero-Shot Learners? A Study on Their Potential and Limitations

no code implementations29 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.

DM-CT: Consistency Training with Data and Model Perturbation

no code implementations29 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.

Data Augmentation Image Classification +2

GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds

no code implementations24 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.

Semantic Segmentation

Why Don't You Click: Neural Correlates of Non-Click Behaviors in Web Search

no code implementations22 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).


Physics-informed Neural Network for Nonlinear Dynamics in Fiber Optics

no code implementations1 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.

Towards a Better Understanding Human Reading Comprehension with Brain Signals

1 code implementation3 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.

EEG Information Retrieval +3

Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

5 code implementations2 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.

Information Retrieval Quantization +1

Exploiting Rich Syntax for Better Knowledge Base Question Answering

no code implementations16 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.

Knowledge Base Question Answering

Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning

no code implementations13 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.

reinforcement-learning reinforcement Learning

Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction

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.

Bilingual Lexicon Induction Word Embeddings

A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents

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.

Multi-Task Learning Opinion Mining

An In-depth Study on Internal Structure of Chinese Words

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.

Optimizing Dense Retrieval Model Training with Hard Negatives

4 code implementations16 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.

Information Retrieval Representation Learning +1

Not All Attention Is All You Need

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.

Document Classification Named Entity Recognition +1

Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots

no code implementations17 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).

Representation Learning Retrieval

R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method

1 code implementation15 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.

Dimensionality Reduction Point Cloud Registration +1

Cortical Surface Shape Analysis Based on Alexandrov Polyhedra

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).

Code Summarization with Structure-induced Transformer

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.

Code Summarization Natural Language Understanding +1

LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding

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.

Document Image Classification Document Layout Analysis +4

THUIR@COLIEE-2020: Leveraging Semantic Understanding and Exact Matching for Legal Case Retrieval and Entailment

no code implementations24 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.


Multi-grained Chinese Word Segmentation with Weakly Labeled Data

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.

Chinese Word Segmentation

Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations

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.

Dependency Parsing Domain Adaptation +1

Improving Relation Extraction with Relational Paraphrase Sentences

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.

Relation Extraction

Semantic Role Labeling with Heterogeneous Syntactic Knowledge

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.

Semantic Role Labeling

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction

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.

Relation Extraction

Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View

1 code implementation30 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.

Face Recognition Image Classification +2

Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently

2 code implementations20 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.

Passage Retrieval Retrieval

Tight Lower Complexity Bounds for Strongly Convex Finite-Sum Optimization

no code implementations17 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.

Improving AMR Parsing with Sequence-to-Sequence Pre-training

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)

AMR Parsing Machine Translation +1

A new dataset of dog breed images and a benchmark for fine-grained classification

1 code implementation1 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.

Classification Fine-Grained Image Classification +2

Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition

1 code implementation10 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.

Metric Learning

Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)

no code implementations2 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.

Point Cloud Registration

Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation

no code implementations2 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.

Classification General Classification +1

Neural Logic Reasoning

3 code implementations20 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.

Logical Reasoning Recommendation Systems

Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels

no code implementations16 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.

Autonomous Driving Medical Diagnosis

Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences

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.

Machine Translation Translation +1

Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks

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.

Fine-Grained Opinion Analysis Multi-Task Learning

Jointly Non-Sampling Learning for Knowledge Graph Enhanced Recommendation

2 code implementations1 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.

Knowledge Graph Embedding Knowledge Graphs +2

Aspect Sentiment Classification with Document-level Sentiment Preference Modeling

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.

Classification General Classification +2

RepBERT: Contextualized Text Embeddings for First-Stage Retrieval

3 code implementations28 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.

Passage Ranking Retrieval

Efficient Second-Order TreeCRF for Neural Dependency Parsing

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.

Chinese Dependency Parsing Dependency Parsing

Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?

1 code implementation6 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.

Dependency Parsing Feature Engineering +3

PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification

2 code implementations9 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.

3D Classification 3D Point Cloud Classification +2

Stochastic Item Descent Method for Large Scale Equal Circle Packing Problem

no code implementations22 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.

AE-OT-GAN: Training GANs from data specific latent distribution

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.