Search Results for author: Zheng Yuan

Found 77 papers, 39 papers with code

Document-level grammatical error correction

1 code implementation EACL (BEA) 2021 Zheng Yuan, Christopher Bryant

Document-level context can provide valuable information in grammatical error correction (GEC), which is crucial for correcting certain errors and resolving inconsistencies.

Grammatical Error Correction NMT +1

Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems

1 code implementation EMNLP 2021 Zheng Yuan, Shiva Taslimipoor, Christopher Davis, Christopher Bryant

In this paper, we show how a multi-class grammatical error detection (GED) system can be used to improve grammatical error correction (GEC) for English.

Grammatical Error Detection NMT +1

Grammatical Error Correction for Code-Switched Sentences by Learners of English

1 code implementation18 Apr 2024 Kelvin Wey Han Chan, Christopher Bryant, Li Nguyen, Andrew Caines, Zheng Yuan

Through this exploration, we propose a novel method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora.

Can We Catch the Elephant? The Evolvement of Hallucination Evaluation on Natural Language Generation: A Survey

no code implementations18 Apr 2024 Siya Qi, Yulan He, Zheng Yuan

Hallucination in Natural Language Generation (NLG) is like the elephant in the room, obvious but often overlooked until recent achievements significantly improved the fluency and grammatical accuracy of generated text.

Hallucination Hallucination Evaluation +1

Language Proficiency and F0 Entrainment: A Study of L2 English Imitation in Italian, French, and Slovak Speakers

no code implementations16 Apr 2024 Zheng Yuan, Štefan Beňuš, Alessandro D'Ausilio

This study explores F0 entrainment in second language (L2) English speech imitation during an Alternating Reading Task (ART).

Dynamic Time Warping

ART: The Alternating Reading Task Corpus for Speech Entrainment and Imitation

no code implementations3 Apr 2024 Zheng Yuan, Dorina De Jong, Štefan Beňuš, Noël Nguyen, Ruitao Feng, Róbert Sabo, Luciano Fadiga, Alessandro D`Ausilio

We introduce the Alternating Reading Task (ART) Corpus, a collection of dyadic sentence reading for studying the entrainment and imitation behaviour in speech communication.

Sentence

Assessing the Efficacy of Grammar Error Correction: A Human Evaluation Approach in the Japanese Context

no code implementations28 Feb 2024 Qiao Wang, Zheng Yuan

In this study, we evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students' writing samples.

Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM

no code implementations18 Feb 2024 Zijin Hong, Zheng Yuan, Hao Chen, Qinggang Zhang, Feiran Huang, Xiao Huang

Generating accurate SQL for user queries (text-to-SQL) is a long-standing problem since the generation of the SQL requires comprehending the query and database and retrieving the accurate data from the database accordingly.

Text-To-SQL

Multi-Behavior Collaborative Filtering with Partial Order Graph Convolutional Networks

no code implementations12 Feb 2024 Yijie Zhang, Yuanchen Bei, Hao Chen, Qijie Shen, Zheng Yuan, Huan Gong, Senzhang Wang, Feiran Huang, Xiao Huang

POG defines the partial order relation of multiple behaviors and models behavior combinations as weighted edges to merge separate behavior graphs into a joint POG.

Collaborative Filtering Recommendation Systems

Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness

1 code implementation9 Jan 2024 Sibo Wang, Jie Zhang, Zheng Yuan, Shiguang Shan

Specifically, PMG-AFT minimizes the distance between the features of adversarial examples in the target model and those in the pre-trained model, aiming to preserve the generalization features already captured by the pre-trained model.

Adversarial Robustness Zero-shot Generalization

FullLoRA-AT: Efficiently Boosting the Robustness of Pretrained Vision Transformers

no code implementations3 Jan 2024 Zheng Yuan, Jie Zhang, Shiguang Shan

In recent years, the Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks, and the robustness of the model has received increasing attention.

Adversarial Robustness

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

no code implementations15 Nov 2023 Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou

Zooter shows computation efficiency in inference as it introduces only a minor computation overhead of a routing function compared with reward model ranking methods.

TAG

Speculative Contrastive Decoding

no code implementations15 Nov 2023 Hongyi Yuan, Keming Lu, Fei Huang, Zheng Yuan, Chang Zhou

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias.

OccuQuest: Mitigating Occupational Bias for Inclusive Large Language Models

1 code implementation25 Oct 2023 Mingfeng Xue, Dayiheng Liu, Kexin Yang, Guanting Dong, Wenqiang Lei, Zheng Yuan, Chang Zhou, Jingren Zhou

Furthermore, we assemble three test sets for comprehensive evaluation, an occu-test set covering 25 occupational categories, an estate set focusing on real estate, and an occu-quora set containing real-world questions from Quora.

Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks

1 code implementation20 Oct 2023 Andrea Sottana, Bin Liang, Kai Zou, Zheng Yuan

Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models.

Grammatical Error Correction Text Simplification

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

2 code implementations9 Oct 2023 Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies.

Code Generation Instruction Following +2

Query and Response Augmentation Cannot Help Out-of-domain Math Reasoning Generalization

1 code implementation9 Oct 2023 Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou

In this paper, we conduct an investigation for such data augmentation in math reasoning and are intended to answer: (1) What strategies of data augmentation are more effective; (2) What is the scaling relationship between the amount of augmented data and model performance; and (3) Can data augmentation incentivize generalization to out-of-domain mathematical reasoning tasks?

Ranked #50 on Math Word Problem Solving on MATH (using extra training data)

Arithmetic Reasoning Data Augmentation +3

NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation

1 code implementation14 Sep 2023 JiaQi Zhang, Yu Cheng, Yongxin Ni, Yunzhu Pan, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, Fajie Yuan

The development of TransRec has encountered multiple challenges, among which the lack of large-scale, high-quality transfer learning recommendation dataset and benchmark suites is one of the biggest obstacles.

Descriptive Recommendation Systems +1

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

1 code implementation14 Aug 2023 Keming Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, Jingren Zhou

Based on this observation, we propose a data selector based on InsTag to select 6K diverse and complex samples from open-source datasets and fine-tune models on InsTag-selected data.

Instruction Following TAG

Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

1 code implementation3 Aug 2023 Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Keming Lu, Chuanqi Tan, Chang Zhou, Jingren Zhou

We find with augmented samples containing more distinct reasoning paths, RFT improves mathematical reasoning performance more for LLMs.

Ranked #100 on Arithmetic Reasoning on GSM8K (using extra training data)

Arithmetic Reasoning GSM8K +1

On the application of Large Language Models for language teaching and assessment technology

no code implementations17 Jul 2023 Andrew Caines, Luca Benedetto, Shiva Taslimipoor, Christopher Davis, Yuan Gao, Oeistein Andersen, Zheng Yuan, Mark Elliott, Russell Moore, Christopher Bryant, Marek Rei, Helen Yannakoudakis, Andrew Mullooly, Diane Nicholls, Paula Buttery

The recent release of very large language models such as PaLM and GPT-4 has made an unprecedented impact in the popular media and public consciousness, giving rise to a mixture of excitement and fear as to their capabilities and potential uses, and shining a light on natural language processing research which had not previously received so much attention.

Grammatical Error Correction Misinformation +1

Hierarchical Pretraining for Biomedical Term Embeddings

no code implementations1 Jul 2023 Bryan Cai, Sihang Zeng, Yucong Lin, Zheng Yuan, Doudou Zhou, Lu Tian

Electronic health records (EHR) contain narrative notes that provide extensive details on the medical condition and management of patients.

Decision Making Knowledge Graphs +3

DiffDTM: A conditional structure-free framework for bioactive molecules generation targeted for dual proteins

no code implementations24 Jun 2023 Lei Huang, Zheng Yuan, Huihui Yan, Rong Sheng, Linjing Liu, Fuzhou Wang, Weidun Xie, Nanjun Chen, Fei Huang, Songfang Huang, Ka-Chun Wong, Yaoyun Zhang

However, molecule generation targeted for dual protein targets still faces formidable challenges including protein 3D structure data requisition for model training, auto-regressive sampling, and model generalization for unseen targets.

The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues

no code implementations12 Jun 2023 Anaïs Tack, Ekaterina Kochmar, Zheng Yuan, Serge Bibauw, Chris Piech

This paper describes the results of the first shared task on the generation of teacher responses in educational dialogues.

Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit

1 code implementation8 Jun 2023 Xinhang Li, Yiying Yang, Zheng Yuan, Zhe Wang, Qinwen Wang, Chen Xu, Lei LI, Jianhua He, Lin Zhang

For the more challenging problem of pursuing multiple evading vehicles, these algorithms typically select a fixed target evading vehicle for pursuing vehicles without considering dynamic traffic situation, which significantly reduces pursuing success rate.

Multi-agent Reinforcement Learning reinforcement-learning

The ADAIO System at the BEA-2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues

no code implementations8 Jun 2023 Adaeze Adigwe, Zheng Yuan

This paper presents the ADAIO team's system entry in the Building Educational Applications (BEA) 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues.

Few-Shot Learning Response Generation

The ART of Conversation: Measuring Phonetic Convergence and Deliberate Imitation in L2-Speech with a Siamese RNN

1 code implementation8 Jun 2023 Zheng Yuan, Aldo Pastore, Dorina De Jong, Hao Xu, Luciano Fadiga, Alessandro D'Ausilio

Phonetic convergence describes the automatic and unconscious speech adaptation of two interlocutors in a conversation.

Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights

no code implementations19 May 2023 Ruyu Li, Wenhao Deng, Yu Cheng, Zheng Yuan, JiaQi Zhang, Fajie Yuan

Furthermore, we compare the performance of the TCF paradigm utilizing the most powerful LMs to the currently dominant ID embedding-based paradigm and investigate the transferability of this TCF paradigm.

Collaborative Filtering News Recommendation +1

Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation

no code implementations24 Apr 2023 Chen Zhao, Wei-Ling Cai, Zheng Yuan, Cheng-Wei Hu

Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks.

Contrastive Learning Data Augmentation +2

RRHF: Rank Responses to Align Language Models with Human Feedback without tears

1 code implementation11 Apr 2023 Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, Fei Huang

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models.

Language Modelling Large Language Model

Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited

1 code implementation24 Mar 2023 Zheng Yuan, Fajie Yuan, Yu Song, Youhua Li, Junchen Fu, Fei Yang, Yunzhu Pan, Yongxin Ni

In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency.

Recommendation Systems

Exploring Partial Knowledge Base Inference in Biomedical Entity Linking

1 code implementation18 Mar 2023 Hongyi Yuan, Keming Lu, Zheng Yuan

Biomedical entity linking (EL) consists of named entity recognition (NER) and named entity disambiguation (NED).

Entity Disambiguation Entity Linking +3

How well do Large Language Models perform in Arithmetic tasks?

1 code implementation16 Mar 2023 Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang

Large language models have emerged abilities including chain-of-thought to answer math word problems step by step.

Math

RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training

1 code implementation1 Mar 2023 Zheng Yuan, Qiao Jin, Chuanqi Tan, Zhengyun Zhao, Hongyi Yuan, Fei Huang, Songfang Huang

We propose to retrieve similar image-text pairs based on ITC from pretraining datasets and introduce a novel retrieval-attention module to fuse the representation of the image and the question with the retrieved images and texts.

Question Answering Retrieval +1

An Extended Sequence Tagging Vocabulary for Grammatical Error Correction

2 code implementations12 Feb 2023 Stuart Mesham, Christopher Bryant, Marek Rei, Zheng Yuan

We extend a current sequence-tagging approach to Grammatical Error Correction (GEC) by introducing specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms.

Grammatical Error Correction Morphological Inflection +1

Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling

no code implementations2 Feb 2023 Zheng Yuan, Yaoyun Zhang, Chuanqi Tan, Wei Wang, Fei Huang, Songfang Huang

To alleviate this limitation, we propose Moleformer, a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them using rotational and translational invariant geometry-aware spatial encoding.

Initial Structure to Relaxed Energy (IS2RE), Direct

HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation

1 code implementation17 Dec 2022 Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang, Songfang Huang

Unlike previous works that only add noise to inputs or parameters, we argue that the hidden representations of Transformers layers convey more diverse and meaningful language information.

Language Modelling Natural Language Inference

Graded-Q Reinforcement Learning with Information-Enhanced State Encoder for Hierarchical Collaborative Multi-Vehicle Pursuit

1 code implementation24 Oct 2022 Yiying Yang, Xinhang Li, Zheng Yuan, Qinwen Wang, Chen Xu, Lin Zhang

However, existing works on MVP pay little attention to the importance of information exchange and cooperation among pursuing vehicles under the complex urban traffic environment.

Decision Making

Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning

1 code implementation NAACL 2022 Hongyi Yuan, Zheng Yuan, Sheng Yu

Entities lie in the heart of biomedical natural language understanding, and the biomedical entity linking (EL) task remains challenging due to the fine-grained and diversiform concept names.

Entity Linking Natural Language Understanding

BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model

1 code implementation BioNLP (ACL) 2022 Hongyi Yuan, Zheng Yuan, Ruyi Gan, Jiaxing Zhang, Yutao Xie, Sheng Yu

Furthermore, we conduct ablation studies on the pretraining tasks for BioBART and find that sentence permutation has negative effects on downstream tasks.

Entity Linking Language Modelling +6

BIOS: An Algorithmically Generated Biomedical Knowledge Graph

no code implementations18 Mar 2022 Sheng Yu, Zheng Yuan, Jun Xia, Shengxuan Luo, Huaiyuan Ying, Sihang Zeng, Jingyi Ren, Hongyi Yuan, Zhengyun Zhao, Yucong Lin, Keming Lu, Jing Wang, Yutao Xie, Heung-Yeung Shum

For decades, these knowledge graphs have been developed via expert curation; however, this method can no longer keep up with today's AI development, and a transition to algorithmically generated BioMedKGs is necessary.

BIG-bench Machine Learning Knowledge Graphs +3

$ \text{T}^3 $OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area

1 code implementation1 Mar 2022 Zheng Yuan, Tianhao Wu, Qinwen Wang, Yiying Yang, Lei LI, Lin Zhang

Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games.

Decision Making

Adaptive Image Transformations for Transfer-based Adversarial Attack

2 code implementations27 Nov 2021 Zheng Yuan, Jie Zhang, Shiguang Shan

Adversarial attacks provide a good way to study the robustness of deep learning models.

Adversarial Attack

Adaptive Perturbation for Adversarial Attack

no code implementations27 Nov 2021 Zheng Yuan, Jie Zhang, Zhaoyan Jiang, Liangliang Li, Shiguang Shan

Instead of using the sign function, we propose to directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations.

Adversarial Attack

MetaHistoSeg: A Python Framework for Meta Learning in Histopathology Image Segmentation

no code implementations29 Sep 2021 Zheng Yuan, Andre Esteva, ran Xu

We also curate a histopathology meta dataset - a benchmark dataset for training and validating models on out-of-distribution performance across a range of cancer types.

Domain Generalization Few-Shot Learning +3

Cambridge at SemEval-2021 Task 2: Neural WiC-Model with Data Augmentation and Exploration of Representation

no code implementations SEMEVAL 2021 Zheng Yuan, David Strohmaier

This paper describes the system of the Cambridge team submitted to the SemEval-2021 shared task on Multilingual and Cross-lingual Word-in-Context Disambiguation.

Data Augmentation Language Modelling +1

Neural sequence modelling for learner error prediction

no code implementations WS 2018 Zheng Yuan

This paper describes our use of two recurrent neural network sequence models: sequence labelling and sequence-to-sequence models, for the prediction of future learner errors in our submission to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM).

Grammatical Error Detection Language Acquisition

Cannot find the paper you are looking for? You can Submit a new open access paper.