Search Results for author: Min Zhang

Found 404 papers, 183 papers with code

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.

Binary Classification TAG

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.

Decoder Machine Translation +2

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).

Relation Sentiment Analysis +1

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

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

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。”

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).

Translation

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

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 +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 +1

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 +2

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.

Decoder NMT +1

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 +2

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 Decoder +1

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

From Role-Play to Drama-Interaction: An LLM Solution

no code implementations23 May 2024 Weiqi Wu, Hongqiu Wu, Lai Jiang, XingYuan Liu, Jiale Hong, Hai Zhao, Min Zhang

Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts.

Instruction Following

Why Not Transform Chat Large Language Models to Non-English?

1 code implementation22 May 2024 Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin Guo, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Min Zhang, Hao Yang, Xinglin Lyu, Jiajun Chen, ShuJian Huang

For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters.

Knowledge Distillation

Fennec: Fine-grained Language Model Evaluation and Correction Extended through Branching and Bridging

1 code implementation20 May 2024 Xiaobo Liang, Haoke Zhang, Helan Hu, Juntao Li, Jun Xu, Min Zhang

The rapid advancement of large language models has given rise to a plethora of applications across a myriad of real-world tasks, mainly centered on aligning with human intent.

Language Modelling

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts

1 code implementation18 May 2024 Yunxin Li, Shenyuan Jiang, Baotian Hu, Longyue Wang, Wanqi Zhong, Wenhan Luo, Lin Ma, Min Zhang

Although the Mixture of Experts (MoE) architecture has been employed to efficiently scale large language and image-text models, these efforts typically involve fewer experts and limited modalities.

Double Correction Framework for Denoising Recommendation

1 code implementation18 May 2024 Zhuangzhuang He, Yifan Wang, Yonghui Yang, Peijie Sun, Le Wu, Haoyue Bai, Jinqi Gong, Richang Hong, Min Zhang

To tackle the above limitations, we propose a Double Correction Framework for Denoising Recommendation (DCF), which contains two correction components from views of more precise sample dropping and avoiding more sparse data.

Denoising Model Optimization +1

Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization

1 code implementation17 May 2024 Yixin Ji, Yang Xiang, Juntao Li, Wei Chen, Zhongyi Liu, Kehai Chen, Min Zhang

To address the challenges of low-rank compression in LLMs, we conduct empirical research on the low-rank characteristics of large models.

Bayesian Optimization Low-rank compression

OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning

1 code implementation9 May 2024 Dan Qiao, Yi Su, Pinzheng Wang, Jing Ye, Wenjing Xie, Yuechi Zhou, Yuyang Ding, Zecheng Tang, Jikai Wang, Yixin Ji, Yue Wang, Pei Guo, Zechen Sun, Zikang Zhang, Juntao Li, Pingfu Chao, Wenliang Chen, Guohong Fu, Guodong Zhou, Qiaoming Zhu, Min Zhang

Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities. However, their massive number of parameters leads to high deployment requirements and incurs significant inference costs, which impedes their practical applications.

Common Sense Reasoning named-entity-recognition +2

VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context

1 code implementation8 May 2024 Yunxin Li, Baotian Hu, Haoyuan Shi, Wei Wang, Longyue Wang, Min Zhang

Large Multimodal Models (LMMs) have achieved impressive success in visual understanding and reasoning, remarkably improving the performance of mathematical reasoning in a visual context.

Math Mathematical Reasoning

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore

no code implementations7 May 2024 Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xuebo Liu, Lidia S. Chao, Min Zhang

The efficacy of an large language model (LLM) generated text detector depends substantially on the availability of sizable training data.

Language Modelling Large Language Model +2

MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation

no code implementations30 Apr 2024 Min Zhang, Haoxuan Li, Fei Wu, Kun Kuang

Out-of-distribution (OOD) problems in few-shot classification (FSC) occur when novel classes sampled from testing distributions differ from base classes drawn from training distributions, which considerably degrades the performance of deep learning models deployed in real-world applications.

Cross-Domain Few-Shot Language Modelling +1

EEG-MACS: Manifold Attention and Confidence Stratification for EEG-based Cross-Center Brain Disease Diagnosis under Unreliable Annotations

no code implementations29 Apr 2024 Zhenxi Song, Ruihan Qin, Huixia Ren, Zhen Liang, Yi Guo, Min Zhang, Zhiguo Zhang

Cross-center data heterogeneity and annotation unreliability significantly challenge the intelligent diagnosis of diseases using brain signals.

EEG

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset

1 code implementation29 Apr 2024 Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, DaCheng Tao, Min Zhang

Experimental results show that MMT models trained on our dataset exhibit a greater ability to exploit visual information than those trained on other MMT datasets.

Multimodal Machine Translation Sentence +2

Semi-supervised Text-based Person Search

no code implementations28 Apr 2024 Daming Gao, Yang Bai, Min Cao, Hao Dou, Mang Ye, Min Zhang

Text-based person search (TBPS) aims to retrieve images of a specific person from a large image gallery based on a natural language description.

Image Captioning Person Search +2

A User-Centric Benchmark for Evaluating Large Language Models

1 code implementation22 Apr 2024 Jiayin Wang, Fengran Mo, Weizhi Ma, Peijie Sun, Min Zhang, Jian-Yun Nie

To address this oversight, we propose benchmarking LLMs from a user perspective in both dataset construction and evaluation designs.

Benchmarking

In-Context Learning State Vector with Inner and Momentum Optimization

1 code implementation17 Apr 2024 Dongfang Li, Zhenyu Liu, Xinshuo Hu, Zetian Sun, Baotian Hu, Min Zhang

In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector.

In-Context Learning Test-time Adaptation

Collaborative-Enhanced Prediction of Spending on Newly Downloaded Mobile Games under Consumption Uncertainty

no code implementations12 Apr 2024 Peijie Sun, Yifan Wang, Min Zhang, Chuhan Wu, Yan Fang, Hong Zhu, Yuan Fang, Meng Wang

In summary, our contributions underscore the importance of stable model training frameworks and the efficacy of collaborative-enhanced models in predicting user spending behavior in mobile gaming.

Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training

2 code implementations8 Apr 2024 Longhui Zhang, Dingkun Long, Meishan Zhang, Yanzhao Zhang, Pengjun Xie, Min Zhang

Experimental results on Chinese sequence labeling datasets demonstrate that the improved BABERT variant outperforms the vanilla version, not only on these tasks but also more broadly across a range of Chinese natural language understanding tasks.

Language Modelling Natural Language Understanding

Cross-Domain Audio Deepfake Detection: Dataset and Analysis

no code implementations7 Apr 2024 Yuang Li, Min Zhang, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Hao Yang

Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy.

DeepFake Detection Face Swapping

Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems

no code implementations2 Apr 2024 Dapeng Zhi, Peixin Wang, Si Liu, Luke Ong, Min Zhang

We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds.

valid

EEG-SVRec: An EEG Dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation

no code implementations1 Apr 2024 Shaorun Zhang, Zhiyu He, Ziyi Ye, Peijie Sun, Qingyao Ai, Min Zhang, Yiqun Liu

To address these challenges and provide a more comprehensive understanding of user affective experience and cognitive activity, we propose EEG-SVRec, the first EEG dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation.

EEG Recommendation Systems

Instruction-Driven Game Engines on Large Language Models

1 code implementation30 Mar 2024 Hongqiu Wu, Y. Wang, XingYuan Liu, Hai Zhao, Min Zhang

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game rules and autonomously generate game-play processes.

Language Modelling Large Language Model

Aiming at the Target: Filter Collaborative Information for Cross-Domain Recommendation

no code implementations29 Mar 2024 Hanyu Li, Weizhi Ma, Peijie Sun, Jiayu Li, Cunxiang Yin, Yancheng He, Guoqiang Xu, Min Zhang, Shaoping Ma

In CUT, user similarity in the target domain is adopted as a constraint for user transformation learning to filter the user collaborative information from the source domain.

Improving Attributed Text Generation of Large Language Models via Preference Learning

no code implementations27 Mar 2024 Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content.

Misinformation Retrieval +2

Sequential Recommendation with Latent Relations based on Large Language Model

1 code implementation27 Mar 2024 Shenghao Yang, Weizhi Ma, Peijie Sun, Qingyao Ai, Yiqun Liu, Mingchen Cai, Min Zhang

Different from previous relation-aware models that rely on predefined rules, we propose to leverage the Large Language Model (LLM) to provide new types of relations and connections between items.

Collaborative Filtering Knowledge Graphs +4

A Situation-aware Enhancer for Personalized Recommendation

1 code implementation27 Mar 2024 Jiayu Li, Peijie Sun, Chumeng Jiang, Weizhi Ma, Qingyao Ai, Min Zhang

In this paper, we provide a new perspective that takes situations as the preconditions for users' interactions.

Recommendation Systems

Common Sense Enhanced Knowledge-based Recommendation with Large Language Model

1 code implementation27 Mar 2024 Shenghao Yang, Weizhi Ma, Peijie Sun, Min Zhang, Qingyao Ai, Yiqun Liu, Mingchen Cai

Knowledge-based recommendation models effectively alleviate the data sparsity issue leveraging the side information in the knowledge graph, and have achieved considerable performance.

Common Sense Reasoning Knowledge Graphs +2

To Recommend or Not: Recommendability Identification in Conversations with Pre-trained Language Models

1 code implementation27 Mar 2024 Zhefan Wang, Weizhi Ma, Min Zhang

First, we propose and define the recommendability identification task, which investigates the need for recommendations in the current conversational context.

Recommendation Systems

From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation

no code implementations21 Mar 2024 Haofei Zhao, Yilun Liu, Shimin Tao, Weibin Meng, Yimeng Chen, Xiang Geng, Chang Su, Min Zhang, Hao Yang

Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT.

Machine Translation Sentence

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

1 code implementation21 Mar 2024 Han Zhao, Min Zhang, Wei Zhao, Pengxiang Ding, Siteng Huang, Donglin Wang

In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success.

Language Modelling Large Language Model

GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning

1 code implementation18 Mar 2024 Xiaojie Li, Yibo Yang, Xiangtai Li, Jianlong Wu, Yue Yu, Bernard Ghanem, Min Zhang

To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics.

Contrastive Learning Data Augmentation +1

Evaluation Ethics of LLMs in Legal Domain

no code implementations17 Mar 2024 Ruizhe Zhang, Haitao Li, Yueyue Wu, Qingyao Ai, Yiqun Liu, Min Zhang, Shaoping Ma

In recent years, the utilization of large language models for natural language dialogue has gained momentum, leading to their widespread adoption across various domains.

Ethics

Backdoor Attack with Mode Mixture Latent Modification

no code implementations12 Mar 2024 Hongwei Zhang, Xiaoyin Xu, Dongsheng An, Xianfeng GU, Min Zhang

Backdoor attacks become a significant security concern for deep neural networks in recent years.

Backdoor Attack Image Classification

Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder

no code implementations27 Feb 2024 Jiaqi Wang, Zhenxi Song, Zhengyu Ma, Xipeng Qiu, Min Zhang, Zhiguo Zhang

Reconstructing natural language from non-invasive electroencephalography (EEG) holds great promise as a language decoding technology for brain-computer interfaces (BCIs).

Brain Decoding EEG +2

Rethinking Negative Instances for Generative Named Entity Recognition

2 code implementations26 Feb 2024 Yuyang Ding, Juntao Li, Pinzheng Wang, Zecheng Tang, Bowen Yan, Min Zhang

In the Named Entity Recognition (NER) task, recent advancements have seen the remarkable improvement of LLMs in a broad range of entity domains via instruction tuning, by adopting entity-centric schema.

named-entity-recognition Named Entity Recognition +2

SelectIT: Selective Instruction Tuning for Large Language Models via Uncertainty-Aware Self-Reflection

1 code implementation26 Feb 2024 Liangxin Liu, Xuebo Liu, Derek F. Wong, Dongfang Li, Ziyi Wang, Baotian Hu, Min Zhang

In this work, we propose a novel approach, termed SelectIT, that capitalizes on the foundational capabilities of the LLM itself.

DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators

no code implementations23 Feb 2024 Xinglin Lyu, Junhui Li, Yanqing Zhao, Daimeng Wei, Shimin Tao, Hao Yang, Min Zhang

In this paper, we propose an alternative adaptation approach, named Decoding-enhanced Multi-phase Prompt Tuning (DeMPT), to make LLMs discriminately model and utilize the inter- and intra-sentence context and more effectively adapt LLMs to context-aware NMT.

Decoder Machine Translation +2

Multi-Agent Collaboration Framework for Recommender Systems

1 code implementation23 Feb 2024 Zhefan Wang, Yuanqing Yu, Wendi Zheng, Weizhi Ma, Min Zhang

LLM-based agents have gained considerable attention for their decision-making skills and ability to handle complex tasks.

Decision Making Explanation Generation +1

Recommender for Its Purpose: Repeat and Exploration in Food Delivery Recommendations

no code implementations22 Feb 2024 Jiayu Li, Aixin Sun, Weizhi Ma, Peijie Sun, Min Zhang

This paper emphasizes the importance of dedicated analyses and methods for domain-specific characteristics for the recommender system studies.

Recommendation Systems

Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment

no code implementations21 Feb 2024 Yunxin Li, Xinyu Chen, Baotian Hu, Haoyuan Shi, Min Zhang

Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e. g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i. e., connecting visuals to their relevant knowledge.

Language Modelling Question Answering +1

LLMs Meet Long Video: Advancing Long Video Comprehension with An Interactive Visual Adapter in LLMs

no code implementations21 Feb 2024 Yunxin Li, Xinyu Chen, Baotain Hu, Min Zhang

Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence.

Video Understanding

A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation

1 code implementation21 Feb 2024 Yunxin Li, Baotian Hu, Wenhan Luo, Lin Ma, Yuxin Ding, Min Zhang

For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description.

In-Context Learning Language Modelling +2

SiLLM: Large Language Models for Simultaneous Machine Translation

1 code implementation20 Feb 2024 Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang, Yang Feng

We propose SiLLM, which delegates the two sub-tasks to separate agents, thereby incorporating LLM into SiMT.

Machine Translation Sentence +1

DB-LLM: Accurate Dual-Binarization for Efficient LLMs

no code implementations19 Feb 2024 Hong Chen, Chengtao Lv, Liang Ding, Haotong Qin, Xiabin Zhou, Yifu Ding, Xuebo Liu, Min Zhang, Jinyang Guo, Xianglong Liu, DaCheng Tao

Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment.

Binarization Computational Efficiency +1

FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema

1 code implementation19 Feb 2024 Junru Lu, Siyu An, Min Zhang, Yulan He, Di Yin, Xing Sun

In the quest to facilitate the deep intelligence of Large Language Models (LLMs) accessible in final-end user-bot interactions, the art of prompt crafting emerges as a critical yet complex task for the average user.

Case Study: Testing Model Capabilities in Some Reasoning Tasks

no code implementations15 Feb 2024 Min Zhang, Sato Takumi, Jack Zhang, Jun Wang

Large Language Models (LLMs) excel in generating personalized content and facilitating interactive dialogues, showcasing their remarkable aptitude for a myriad of applications.

Unsupervised Sign Language Translation and Generation

no code implementations12 Feb 2024 Zhengsheng Guo, Zhiwei He, Wenxiang Jiao, Xing Wang, Rui Wang, Kehai Chen, Zhaopeng Tu, Yong Xu, Min Zhang

Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data.

Machine Translation Sign Language Translation +1

RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner

no code implementations8 Feb 2024 Ying Zang, Chenglong Fu, Runlong Cao, Didi Zhu, Min Zhang, WenJun Hu, Lanyun Zhu, Tianrun Chen

This pioneering work lays the groundwork for future research in semi-supervised learning for referring expression segmentation.

Image Segmentation Pseudo Label +5

In-Context Learning for Few-Shot Nested Named Entity Recognition

no code implementations2 Feb 2024 Meishan Zhang, Bin Wang, Hao Fei, Min Zhang

In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address.

Contrastive Learning In-Context Learning +7

When Large Language Models Meet Vector Databases: A Survey

no code implementations30 Jan 2024 Zhi Jing, Yongye Su, Yikun Han, Bo Yuan, Haiyun Xu, Chunjiang Liu, Kehai Chen, Min Zhang

This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area.

Hallucination Information Retrieval +1

Revisiting Demonstration Selection Strategies in In-Context Learning

no code implementations22 Jan 2024 Keqin Peng, Liang Ding, Yancheng Yuan, Xuebo Liu, Min Zhang, Yuanxin Ouyang, DaCheng Tao

In this work, we first revisit the factors contributing to this variance from both data and model aspects, and find that the choice of demonstration is both data- and model-dependent.

In-Context Learning

Using Large Language Model for End-to-End Chinese ASR and NER

no code implementations21 Jan 2024 Yuang Li, Jiawei Yu, Yanqing Zhao, Min Zhang, Mengxin Ren, Xiaofeng Zhao, Xiaosong Qiao, Chang Su, Miaomiao Ma, Hao Yang

In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions

no code implementations16 Jan 2024 Yachao Li, Junhui Li, Jing Jiang, Min Zhang

Our proposed translation mixed-instructions enable LLMs (Llama-2~7B and 13B) to maintain consistent translation performance from the sentence level to documents containing as many as 2048 tokens.

Language Modelling Large Language Model +3

HA-HI: Synergising fMRI and DTI through Hierarchical Alignments and Hierarchical Interactions for Mild Cognitive Impairment Diagnosis

1 code implementation2 Jan 2024 Xiongri Shen, Zhenxi Song, Linling Li, Min Zhang, Lingyan Liang Honghai Liu, Demao Deng, Zhiguo Zhang

Early diagnosis of mild cognitive impairment (MCI) and subjective cognitive decline (SCD) utilizing multi-modal magnetic resonance imaging (MRI) is a pivotal area of research.

Expressive Forecasting of 3D Whole-body Human Motions

1 code implementation19 Dec 2023 Pengxiang Ding, Qiongjie Cui, Min Zhang, Mengyuan Liu, Haofan Wang, Donglin Wang

Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications.

Human Pose Forecasting Motion Forecasting

Learning to Reweight for Graph Neural Network

no code implementations19 Dec 2023 Zhengyu Chen, Teng Xiao, Kun Kuang, Zheqi Lv, Min Zhang, Jinluan Yang, Chengqiang Lu, Hongxia Yang, Fei Wu

In this paper, we study the problem of the generalization ability of GNNs in Out-Of-Distribution (OOD) settings.

Out-of-Distribution Generalization

Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingales

no code implementations15 Dec 2023 Dapeng Zhi, Peixin Wang, Cheng Chen, Min Zhang

In this work, we present the first approach for robustness verification of DRL-based control systems by introducing reward martingales, which offer a rigorous mathematical foundation to characterize the impact of state perturbations on system performance in terms of cumulative rewards.

Prompt-based Distribution Alignment for Unsupervised Domain Adaptation

1 code implementation15 Dec 2023 Shuanghao Bai, Min Zhang, Wanqi Zhou, Siteng Huang, Zhirong Luan, Donglin Wang, Badong Chen

Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA.

Prompt Engineering Unsupervised Domain Adaptation

Relevance Feedback with Brain Signals

1 code implementation9 Dec 2023 Ziyi Ye, Xiaohui Xie, Qingyao Ai, Yiqun Liu, Zhihong Wang, Weihang Su, Min Zhang

To explore the effectiveness of brain signals in the context of RF, we propose a novel RF framework that combines BCI-based relevance feedback with pseudo-relevance signals and implicit signals to improve the performance of document re-ranking.

Brain Computer Interface Re-Ranking

Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix

1 code implementation5 Dec 2023 Xinyu Ma, Xuebo Liu, Min Zhang

In multilingual translation research, the comprehension and utilization of language families are of paramount importance.

Clustering Translation

TSRankLLM: A Two-Stage Adaptation of LLMs for Text Ranking

1 code implementation28 Nov 2023 Longhui Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Min Zhang

Text ranking is a critical task in various information retrieval applications, and the recent success of pre-trained language models (PLMs), especially large language models (LLMs), has sparked interest in their application to text ranking.

Decoder Information Retrieval +1

Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs

no code implementations27 Nov 2023 Yunxin Li, Baotian Hu, Wei Wang, Xiaochun Cao, Min Zhang

These models predominantly map visual information into language representation space, leveraging the vast knowledge and powerful text generation abilities of LLMs to produce multimodal instruction-following responses.

Instruction Following multimodal generation +1

Addressing the Length Bias Problem in Document-Level Neural Machine Translation

no code implementations20 Nov 2023 Zhuocheng Zhang, Shuhao Gu, Min Zhang, Yang Feng

To solve the length bias problem, we propose to improve the DNMT model in training method, attention mechanism, and decoding strategy.

Machine Translation Translation

Language Generation from Brain Recordings

1 code implementation16 Nov 2023 Ziyi Ye, Qingyao Ai, Yiqun Liu, Maarten de Rijke, Min Zhang, Christina Lioma, Tuukka Ruotsalo

Inspired by recent research that revealed associations between the brain and the large computational language models, we propose a generative language BCI that utilizes the capacity of a large language model (LLM) jointly with a semantic brain decoder to directly generate language from functional magnetic resonance imaging (fMRI) input.

Decoder Language Modelling +3

Temporal Knowledge Question Answering via Abstract Reasoning Induction

no code implementations15 Nov 2023 Ziyang Chen, Dongfang Li, Xiang Zhao, Baotian Hu, Min Zhang

In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs).

Question Answering

How Well Do Large Language Models Understand Syntax? An Evaluation by Asking Natural Language Questions

1 code implementation14 Nov 2023 Houquan Zhou, Yang Hou, Zhenghua Li, Xuebin Wang, Zhefeng Wang, Xinyu Duan, Min Zhang

While recent advancements in large language models (LLMs) bring us closer to achieving artificial general intelligence, the question persists: Do LLMs truly understand language, or do they merely mimic comprehension through pattern recognition?

Prepositional Phrase Attachment Question Answering +1

Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration

1 code implementation14 Nov 2023 Zhenran Xu, Senbao Shi, Baotian Hu, Jindi Yu, Dongfang Li, Min Zhang, Yuxiang Wu

Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks.

Math

A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering

no code implementations13 Nov 2023 Yunxin Li, Longyue Wang, Baotian Hu, Xinyu Chen, Wanqi Zhong, Chenyang Lyu, Wei Wang, Min Zhang

The emergence of multimodal large models (MLMs) has significantly advanced the field of visual understanding, offering remarkable capabilities in the realm of visual question answering (VQA).

Decision Making General Knowledge +3

Context Consistency between Training and Testing in Simultaneous Machine Translation

1 code implementation13 Nov 2023 Meizhi Zhong, Lemao Liu, Kehai Chen, Mingming Yang, Min Zhang

Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context.

Machine Translation Translation

Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction

no code implementations10 Nov 2023 Xilai Ma, Jing Li, Min Zhang

In this paper, we propose a novel approach for few-shot relation extraction using large language models, named CoT-ER, chain-of-thought with explicit evidence reasoning.

In-Context Learning Meta-Learning +2

Mirror: A Universal Framework for Various Information Extraction Tasks

1 code implementation9 Nov 2023 Tong Zhu, Junfei Ren, Zijian Yu, Mengsong Wu, Guoliang Zhang, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Min Zhang

Sharing knowledge between information extraction tasks has always been a challenge due to the diverse data formats and task variations.

Machine Reading Comprehension

A Survey of Large Language Models Attribution

1 code implementation7 Nov 2023 Dongfang Li, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Ziyang Chen, Baotian Hu, Aiguo Wu, Min Zhang

Open-domain generative systems have gained significant attention in the field of conversational AI (e. g., generative search engines).

LLM-enhanced Self-training for Cross-domain Constituency Parsing

1 code implementation5 Nov 2023 Jianling Li, Meishan Zhang, Peiming Guo, Min Zhang, Yue Zhang

Our experimental results demonstrate that self-training for constituency parsing, equipped with an LLM, outperforms traditional methods regardless of the LLM's performance.

Constituency Parsing Language Modelling +1

Caseformer: Pre-training for Legal Case Retrieval Based on Inter-Case Distinctions

1 code implementation1 Nov 2023 Weihang Su, Qingyao Ai, Yueyue Wu, Yixiao Ma, Haitao Li, Yiqun Liu, Zhijing Wu, Min Zhang

Legal case retrieval aims to help legal workers find relevant cases related to their cases at hand, which is important for the guarantee of fairness and justice in legal judgments.

Fairness Retrieval

Non-autoregressive Streaming Transformer for Simultaneous Translation

1 code implementation23 Oct 2023 Zhengrui Ma, Shaolei Zhang, Shoutao Guo, Chenze Shao, Min Zhang, Yang Feng

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality.

Decoder Machine Translation +1

Improving Seq2Seq Grammatical Error Correction via Decoding Interventions

1 code implementation23 Oct 2023 Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang

In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token.

Decoder Grammatical Error Correction +1

Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting

1 code implementation20 Oct 2023 Zecheng Tang, Kaifeng Qi, Juntao Li, Min Zhang

By leveraging the augmenting data from the GEC models themselves in the post-training process and introducing regularization data for cycle training, our proposed method can effectively improve the model robustness of well-trained GEC models with only a few more training epochs as an extra cost.

Adversarial Attack Grammatical Error Correction

Revisiting Sparse Retrieval for Few-shot Entity Linking

1 code implementation19 Oct 2023 Yulin Chen, Zhenran Xu, Baotian Hu, Min Zhang

Entity linking aims to link ambiguous mentions to their corresponding entities in a knowledge base.

Entity Linking Retrieval

A Read-and-Select Framework for Zero-shot Entity Linking

1 code implementation19 Oct 2023 Zhenran Xu, Yulin Chen, Baotian Hu, Min Zhang

Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability.

Entity Disambiguation Entity Linking +1

G-SPEED: General SParse Efficient Editing MoDel

1 code implementation16 Oct 2023 Haoke Zhang, Yue Wang, Juntao Li, Xiabing Zhou, Min Zhang

Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages.

Language Models are Universal Embedders

1 code implementation12 Oct 2023 Xin Zhang, Zehan Li, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Min Zhang

As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is desirable to build a unified embedding model rather than dedicated ones for each scenario.

Code Search Language Modelling +2

Empower Nested Boolean Logic via Self-Supervised Curriculum Learning

1 code implementation9 Oct 2023 Hongqiu Wu, Linfeng Liu, Hai Zhao, Min Zhang

Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data.

Logical Reasoning Self-Supervised Learning

Investigating the Influence of Legal Case Retrieval Systems on Users' Decision Process

no code implementations7 Oct 2023 Beining Wang, Ruizhe Zhang, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu

Given a specific query case, legal case retrieval systems aim to retrieve a set of case documents relevant to the case at hand.

Decision Making Information Retrieval +1

Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning

1 code implementation4 Oct 2023 Murong Yue, Jie Zhao, Min Zhang, Liang Du, Ziyu Yao

Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services.

Decision Making Language Modelling +1

OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch

1 code implementation19 Sep 2023 Juntao Li, Zecheng Tang, Yuyang Ding, Pinzheng Wang, Pei Guo, Wangjie You, Dan Qiao, Wenliang Chen, Guohong Fu, Qiaoming Zhu, Guodong Zhou, Min Zhang

This report provides the main details to pre-train an analogous model, including pre-training data processing, Bilingual Flan data collection, the empirical observations that inspire our model architecture design, training objectives of different stages, and other enhancement techniques.

A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting

no code implementations18 Sep 2023 Yuang Li, Yinglu Li, Min Zhang, Chang Su, Mengxin Ren, Xiaosong Qiao, Xiaofeng Zhao, Mengyao Piao, Jiawei Yu, Xinglin Lv, Miaomiao Ma, Yanqing Zhao, Hao Yang

End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations, and terminologies not frequently encountered in the training data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Self-Correlation and Cross-Correlation Learning for Few-Shot Remote Sensing Image Semantic Segmentation

1 code implementation11 Sep 2023 Linhan Wang, Shuo Lei, Jianfeng He, Shengkun Wang, Min Zhang, Chang-Tien Lu

To tackle these challenges, we propose a Self-Correlation and Cross-Correlation Learning Network for the few-shot remote sensing image semantic segmentation.

Few-Shot Learning Segmentation +1

Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models

no code implementations24 Aug 2023 Yue Wang, Xinrui Wang, Juntao Li, Jinxiong Chang, Qishen Zhang, Zhongyi Liu, Guannan Zhang, Min Zhang

Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks.

An Empirical Study of CLIP for Text-based Person Search

1 code implementation19 Aug 2023 Min Cao, Yang Bai, Ziyin Zeng, Mang Ye, Min Zhang

TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS.

Cross-Modal Retrieval Data Augmentation +5

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation

1 code implementation16 Aug 2023 Xinshuo Hu, Dongfang Li, Baotian Hu, Zihao Zheng, Zhenyu Liu, Min Zhang

To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning.

Language Modelling Mathematical Reasoning

CMD: a framework for Context-aware Model self-Detoxification

2 code implementations16 Aug 2023 Zecheng Tang, Keyan Zhou, Juntao Li, Yuyang Ding, Pinzheng Wang, Bowen Yan, Min Zhang

In view of this, we introduce a Context-aware Model self-Detoxification~(CMD) framework that pays attention to both the context and the detoxification process, i. e., first detoxifying the context and then making the language model generate along the safe context.

Language Modelling

Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognition

no code implementations13 Aug 2023 Weishan Ye, Zhiguo Zhang, Min Zhang, Fei Teng, Li Zhang, Linling Li, Gan Huang, Jianhong Wang, Dong Ni, Zhen Liang

In this paper, a semi-supervised Dual-stream Self-Attentive Adversarial Graph Contrastive learning framework (termed as DS-AGC) is proposed to tackle the challenge of limited labeled data in cross-subject EEG-based emotion recognition.

Contrastive Learning Domain Adaptation +2

Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling

no code implementations9 Aug 2023 Yu Zhao, Hao Fei, Yixin Cao, Bobo Li, Meishan Zhang, Jianguo Wei, Min Zhang, Tat-Seng Chua

A scene-event mapping mechanism is first designed to bridge the gap between the underlying scene structure and the high-level event semantic structure, resulting in an overall hierarchical scene-event (termed ICE) graph structure.

Semantic Role Labeling

XNLP: An Interactive Demonstration System for Universal Structured NLP

no code implementations3 Aug 2023 Hao Fei, Meishan Zhang, Min Zhang, Tat-Seng Chua

Structured Natural Language Processing (XNLP) is an important subset of NLP that entails understanding the underlying semantic or syntactic structure of texts, which serves as a foundational component for many downstream applications.

Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction

1 code implementation24 Jul 2023 Yifan Wang, Peijie Sun, Min Zhang, Qinglin Jia, Jingjie Li, Shaoping Ma

To directly introduce the correct feedback label information, we propose an Unbiased delayed feedback Label Correction framework (ULC), which uses an auxiliary model to correct labels for observed negative feedback samples.

counterfactual

Measuring Item Global Residual Value for Fair Recommendation

1 code implementation17 Jul 2023 Jiayin Wang, Weizhi Ma, Chumeng Jiang, Min Zhang, Yuan Zhang, Biao Li, Peng Jiang

In this paper, we call for a shift of attention from modeling user preferences to developing fair exposure mechanisms for items.

Recommendation Systems

Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking

no code implementations12 Jul 2023 Xuewei Wang, Qiang Jin, Shengyu Huang, Min Zhang, Xi Liu, Zhengli Zhao, Yukun Chen, Zhengyu Zhang, Jiyan Yang, Ellie Wen, Sagar Chordia, Wenlin Chen, Qin Huang

In order to pass better ads from the early to the final stage ranking, we propose a multi-task learning framework for early stage ranking to capture multiple final stage ranking components (i. e. ads clicks and ads quality events) and their task relations.

Multi-Task Learning

THUIR2 at NTCIR-16 Session Search (SS) Task

no code implementations1 Jul 2023 Weihang Su, Xiangsheng Li, Yiqun Liu, Min Zhang, Shaoping Ma

Our team(THUIR2) participated in both FOSS and POSS subtasks of the NTCIR-161 Session Search (SS) Task.

Language Modelling Learning-To-Rank +1

Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse

no code implementations28 Jun 2023 Didi Zhu, Zexi Li, Min Zhang, Junkun Yuan, Yunfeng Shao, Jiashuo Liu, Kun Kuang, Yinchuan Li, Chao Wu

It is found that NC optimality of text-to-image representations shows a positive correlation with downstream generalizability, which is more severe under class imbalance settings.

Generative Multimodal Entity Linking

1 code implementation22 Jun 2023 Senbao Shi, Zhenran Xu, Baotian Hu, Min Zhang

Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base.

Entity Linking In-Context Learning +1

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

no code implementations ICCV 2023 Jingwen Guo, Hong Liu, Shitong Sun, Tianyu Guo, Min Zhang, Chenyang Si

Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos.

Action Recognition Federated Learning +3

Rethinking Document-Level Relation Extraction: A Reality Check

no code implementations15 Jun 2023 Jing Li, Yequan Wang, Shuai Zhang, Min Zhang

Recently, numerous efforts have continued to push up performance boundaries of document-level relation extraction (DocRE) and have claimed significant progress in DocRE.

Document-level Relation Extraction Relation

Disambiguated Lexically Constrained Neural Machine Translation

no code implementations27 May 2023 Jinpeng Zhang, Nini Xiao, Ke Wang, Chuanqi Dong, Xiangyu Duan, Yuqi Zhang, Min Zhang

Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications.

Data Augmentation Machine Translation +1

Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation

1 code implementation26 May 2023 Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu, Xiangpeng Wei, Dayiheng Liu, Jun Xie, Min Zhang, Jinsong Su

$k$-Nearest neighbor machine translation ($k$NN-MT) has attracted increasing attention due to its ability to non-parametrically adapt to new translation domains.

Domain Adaptation Machine Translation +3

A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation

no code implementations26 May 2023 Zhiyi Xue, Si Liu, Zhaodi Zhang, Yiting Wu, Min Zhang

In this paper, we study existing approaches and identify a dominant factor in defining tight approximation, namely the approximation domain of the activation function.

Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization

no code implementations25 May 2023 Yunze Tong, Junkun Yuan, Min Zhang, Didi Zhu, Keli Zhang, Fei Wu, Kun Kuang

With contrastive learning, we propose a learning potential-guided metric for domain heterogeneity by promoting learning variant features.

Contrastive Learning Domain Generalization

NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts

1 code implementation25 May 2023 Yue Zhang, Bo Zhang, Haochen Jiang, Zhenghua Li, Chen Li, Fei Huang, Min Zhang

We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains.

Grammatical Error Correction

Revisiting Token Dropping Strategy in Efficient BERT Pretraining

1 code implementation24 May 2023 Qihuang Zhong, Liang Ding, Juhua Liu, Xuebo Liu, Min Zhang, Bo Du, DaCheng Tao

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers.

RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search

1 code implementation23 May 2023 Yang Bai, Min Cao, Daming Gao, Ziqiang Cao, Chen Chen, Zhenfeng Fan, Liqiang Nie, Min Zhang

RA offsets the overfitting risk by introducing a novel positive relation detection task (i. e., learning to distinguish strong and weak positive pairs).

Person Search Relation +2

Text-based Person Search without Parallel Image-Text Data

no code implementations22 May 2023 Yang Bai, Jingyao Wang, Min Cao, Chen Chen, Ziqiang Cao, Liqiang Nie, Min Zhang

Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description.

Image Captioning Language Modelling +4