Yiming Cui

Yiming Cui

he/him

Principal Scientist, Vice Dean

Publications

Google Schoalr     Semantic Scholar     dblp     ACL Anthology

Pre-Training with Whole Word Masking for Chinese BERT

  • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), Vol.29. 2021.
  • TLDR: This paper proposed a series of Chinese pre-trained language models with thorough evaluations.
  • ๐ŸŽ‰ Been selected as one of the ESI Highly Cited Papers in Engineering by Clarivateโ„ข.
  • ๐ŸŽ‰ Been selected as one of Top-25 Downloaded Papers in IEEE Signal Processing Society (2021-2023).

๐Ÿ“„ PDF ๐Ÿ”Ž Bib pub IEEE Xplore Chinese-BERT-wwm MacBERT

Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca

  • Yiming Cui, Ziqing Yang, Xin Yao. arXiv pre-print: 2304.08177. 2023.
  • TLDR: This paper proposes Chinese LLaMA and Alpaca models.
  • ๐ŸŽ‰ The open-source projects have been ranked 1st place in GitHub Trending repositories.

๐Ÿ“„ PDF ๐Ÿ”Ž Bib arXiv Chinese-LLaMA-Alpaca Chinese-LLaMA-Alpaca-2 Chinese-LLaMA-Alpaca-3

Attention-over-Attention Neural Networks for Reading Comprehension

  • Yiming Cui, Zhipeng Chen, Si Wei, Shijin Wang, Ting Liu, Guoping Hu. ACL 2017. 2017.
  • TLDR: This paper proposes two-stream attention network (i.e., AoA) for machine reading comprehension.
  • ๐ŸŽ‰ This paper has been selected as one of the Most Influential ACL 2017 Paper (Top 11) by Paper Digest.

๐Ÿ“„ PDF ๐Ÿ”Ž Bib ๐Ÿชง Slides pub ACL Anthology

2025

๐Ÿ“š Natural Language Processing: A Large Language Model Approach (่‡ช็„ถ่ฏญ่จ€ๅค„็†๏ผšๅŸบไบŽๅคง่ฏญ่จ€ๆจกๅž‹็š„ๆ–นๆณ•)

2024

Self-Evolving GPT: A Lifelong Autonomous Experiential Learner

Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral

2023

Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca

Gradient-based Intra-attention Pruning on Pre-trained Language Models

IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning

MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model

2022

LERT: A Linguistically-motivated Pre-trained Language Model

Visualizing Attention Zones in Machine Reading Comprehension Models

  • Yiming Cui, Wei-Nan Zhang, Ting Liu. STAR Protocols, Vol.3. ๐Ÿ”Ž Bib pub

Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models

  • Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhigang Chen, Shijin Wang. iScience, Vol.25. ๐Ÿ”Ž Bib pub GitHub

ExpMRC: Explainability Evaluation for Machine Reading Comprehension

Teaching Machines to Read, Answer and Explain

  • Yiming Cui, Ting Liu, Wanxiang Che, Zhigang Chen, Shijin Wang. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), Vol.30. ๐Ÿ”Ž Bib arXiv pub IEEE Xplore

PERT: Pre-training BERT with Permuted Language Model

Interactive Gated Decoder for Machine Reading Comprehension

  • Yiming Cui, Wanxiang Che, Ziqing Yang, Ting Liu. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol.21. ๐Ÿ”Ž Bib pub ACM DL

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

  • Wei-Nan Zhang, Yiming Cui, Kaiyan Zhang, Yifa Wang, Qingfu Zhu, Lingzhi Li, Ting Liu. ACM Transactions on Information Systems (TOIS). ๐Ÿ”Ž Bib pub ACM DL

TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models

Cross-Lingual Text Classification with Multilingual Distillation and Zero-Shot-Aware Training

  • Ziqing Yang, Yiming Cui, Zhigang Chen, Shijin Wang. arXiv pre-print: 2202.13654. ๐Ÿ”Ž Bib arXiv

CINO: A Chinese Minority Pre-trained Language Model

HFL at SemEval-2022 Task 8: A Linguistics-inspired Regression Model with Data Augmentation for Multilingual News Similarity

  • Zihang Xu, Ziqing Yang, Yiming Cui, Zhigang Chen. SemEval 2022. ๐Ÿ”Ž Bib pub ACL Anthology GitHub
  • ๐ŸŽ‰ This paper has been selected as one of the "Best Paper Honorable Mention Award" at SemEval-2022

HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection

Augmented and challenging datasets with multi-step reasoning and multi-span questions for Chinese judicial reading comprehension

  • Qingye Meng, Ziyue Wang, Hang Chen, Xianzhen Luo, Baoxin Wang, Zhipeng Chen, Yiming Cui, Dayong Wu, Zhigang Chen, Shijin Wang. AI Open, Vol.3. ๐Ÿ”Ž Bib pub ScienceDirect

2021

Highly Influential Pre-Training with Whole Word Masking for Chinese BERT

  • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), Vol.29. ๐Ÿ”Ž Bib pub IEEE Xplore GitHub
  • ๐Ÿ† This paper has been selected as one of the ESI Highly Cited Papers (by Clarivateโ„ข) in Engineering.

Adversarial Training for Machine Reading Comprehension with Virtual Embeddings

Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering

  • Nan Shao, Yiming Cui, Ting Liu, Shijin Wang, Guoping Hu. arXiv pre-print: 2102.03741. ๐Ÿ”Ž Bib arXiv

๐Ÿ“š Natural Language Processing: A Pre-trained Model Approach (่‡ช็„ถ่ฏญ่จ€ๅค„็†๏ผšๅŸบไบŽ้ข„่ฎญ็ปƒๆจกๅž‹็š„ๆ–นๆณ•)

Benchmarking Robustness of Machine Reading Comprehension Models

Bilingual Alignment Pre-training for Zero-shot Cross-lingual Transfer

2020

Discriminative Sentence Modeling for Story Ending Prediction

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension

Revisiting Pre-Trained Models for Chinese Natural Language Processing

  • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu. EMNLP 2020 (Findings). ๐Ÿ”Ž Bib pub ACL Anthology GitHub
  • ๐ŸŽ‰ This paper has been selected as one of the Most Influential EMNLP 2020 Papers (Top 11) by Paper Digest.

CharBERT: Character-aware Pre-trained Language Model

Is Graph Structure Necessary for Multi-hop Question Answering?

Conversational Word Embedding for Retrieval-based Dialog System

TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing

Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting

2019

Cross-Lingual Machine Reading Comprehension

A Span-Extraction Dataset for Chinese Machine Reading Comprehension

Contextual Recurrent Units for Cloze-style Reading Comprehension

  • Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhipeng Chen, Shijin Wang, Guoping Hu. arXiv pre-print: 1911.05960. ๐Ÿ”Ž Bib arXiv

Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions

TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots

Improving Machine Reading Comprehension via Adversarial Training

  • Ziqing Yang, Yiming Cui, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu. arXiv pre-print: 1911.03614. ๐Ÿ”Ž Bib arXiv

Exploiting Persona Information for Diverse Generation of Conversational Responses

CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension

  • Xingyi Duan, Baoxin Wang, Ziyue Wang, Wentao Ma, Yiming Cui, Dayong Wu, Shijin Wang, Ting Liu, Tianxiang Huo, Zhen Hu, Heng Wang, Zhiyuan Liu. CCL 2019. ๐Ÿ”Ž Bib arXiv GitHub

2018

Dataset for the First Evaluation on Chinese Machine Reading Comprehension

Context-Sensitive Generation of Open-Domain Conversational Responses

HFL-RC System at SemEval-2018 Task 11: Hybrid Multi-Aspects Model for Commonsense Reading Comprehension

  • Zhipeng Chen, Yiming Cui*, Wentao Ma, Shijin Wang, Ting Liu, Guoping Hu. arXiv pre-print: 1803.05655. ๐Ÿ”Ž Bib arXiv

A Car Manual Question Answering System based on Neural Network (ๅŸบไบŽ็ฅž็ป็ฝ‘็ปœ็š„ๆฑฝ่ฝฆ่ฏดๆ˜Žไนฆ้—ฎ็ญ”็ณป็ปŸ)

  • Le Qi, Yu Zhang, Wentao Ma, Yiming Cui, Shijin Wang, Ting Liu. Journal of Shanxi University (Natural Science Edition). ๐Ÿ”Ž Bib

2017

Highly Influential Attention-over-Attention Neural Networks for Reading Comprehension

The Brilliant Chinese Achievements in SQuAD Challenge (ๆ–ฏๅฆ็ฆSQuADๆŒ‘ๆˆ˜่ต›็š„ไธญๅ›ฝไบฎไธฝๆฆœๅ•)

  • Yiming Cui, Ting Liu, Shijin Wang, Zhipeng Chen, Wentao Ma, Guoping Hu. Communication of CCF. ๐Ÿ”Ž Bib

Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution

2016

Highly Influential Consensus Attention-based Neural Networks for Chinese Reading Comprehension

LSTM Neural Reordering Feature for Statistical Machine Translation

2015 and earlier

Augmenting Phrase Table by Employing Lexicons for Pivot-based SMT

  • Yiming Cui, Conghui Zhu, Xiaoning Zhu, Tiejun Zhao. arXiv pre-print: 1512.00170. ๐Ÿ”Ž Bib arXiv

Context-extended Phrase Reordering Model for Pivot-based Statistical Machine Translation

The USTC Machine Translation System for IWSLT2014

Phrase Table Combination Deficiency Analyses in Pivot-based SMT

The HIT-LTRC Machine Translation System for IWSLT 2012