“LA-paper-report-talk-etc”的版本间的差异
跳到导航
跳到搜索
| （未显示3个用户的142个中间版本） | |||
| 第14行： | 第14行： | ||
== Talks（报告） == | == Talks（报告） == | ||
| − | * | + | * '''视频尽可能都放在了哔哩哔哩上了（搜用户名：LAGroup）''' |
| − | * | + | * 2024年11月24日受南师大李斌老师邀请做报告（大模型时代如何做研究：一些思考）【文本纠错任务上的大模型相关工作，作为例子】 |
| − | * | + | * 2024年2月1日受邀参加2024阿里云高校前沿技术论坛（大模型时代下文本校对研究的尝试和构想）【小而美的研究工作】 |
| − | * | + | * 2023年4月8日受北语杨天麟老师邀请做报告（大模型时代句法语义研究何去何从） |
| + | * 2022年11月29日受复旦邱锡鹏老师邀请做报告（基于适配句法知识的文本纠错） | ||
| + | * 2022年11月11日受邀对COLING-2022 Best Paper做英文报告【按邀请顺序：新加坡国立大学、新加坡设计与技术大学、南京大学】 | ||
| + | * 2022年8月27日，受邀在江苏省人工智能大会上做报告（汉语文本纠错近年进展：数据集和模型） | ||
| + | |||
* 2021.7.27：《数据标注师资培训》(哈工大大数据集团) | * 2021.7.27：《数据标注师资培训》(哈工大大数据集团) | ||
** [http://hlt.suda.edu.cn/LA/videos/2021-07-26-1+X数据标注师资培训.mp4 培训视频] [https://mp.weixin.qq.com/s/T2HS90jrHs-ly8aCbwj-Eg 数据标注师资培训介绍] | ** [http://hlt.suda.edu.cn/LA/videos/2021-07-26-1+X数据标注师资培训.mp4 培训视频] [https://mp.weixin.qq.com/s/T2HS90jrHs-ly8aCbwj-Eg 数据标注师资培训介绍] | ||
| 第41行： | 第45行： | ||
** [http://hlt.suda.edu.cn/~zhli/2019-9-train/LAGroup.mp4 mp4视频] [http://hlt.suda.edu.cn/~zhli/2019-9-train/zhenghua-2019-9-28-LAGroup.pdf pdf] | ** [http://hlt.suda.edu.cn/~zhli/2019-9-train/LAGroup.mp4 mp4视频] [http://hlt.suda.edu.cn/~zhli/2019-9-train/zhenghua-2019-9-28-LAGroup.pdf pdf] | ||
| − | == | + | == Competition or Shared Tasks == |
| − | * | + | |
| − | + | * 刘亚慧、乔子恒、李正华、龚晨、张民. 2025.8. CCL-2025 第三届汉语框架语义解析评测, 二等奖 [https://tianchi.aliyun.com/competition/entrance/532338/rankingList 比赛榜单]，[http://cips-cl.org/static/CCL2025/cclEval/taskResults/index.html 评测结果] | |
| − | * CCL- | + | |
| − | * | + | * 周厚全，乔子恒，蒋浩辰，刘雨萌. 金山办公2024算法挑战赛-中文文本智能校对大赛，第一名，一等奖 |
| + | |||
| + | * 刘亚慧、龚晨、张民. 2024.8. CCL-2024 第二届汉语框架语义解析（开放赛道）, 一等奖 [https://aclanthology.org/2024.ccl-3.3.pdf 官方评测报告.pdf] ， [https://tianchi.aliyun.com/competition/entrance/532179/rankingList 比赛榜单] | ||
| + | |||
| + | * 王学彬, 李正华. 2024.5. 第一届古汉语断句标点评测（EvaHan2024）评测，二等奖*（COLING-2024 workshop） | ||
| − | |||
| − | * | + | * 辜仰淦，周仕林，李正华. 2023年8月. CCL中文抽象语义表示解析评测（一等奖）[https://aclanthology.org/2023.ccl-3.5 官网评测报告] |
| + | |||
| + | * 蒋浩辰，刘雨萌，周厚全，乔子恒，章波，李辰，李正华，张民. CCL汉语学习者文本纠错评测（封闭、开放双赛道第一）. 2023年8月. [https://aclanthology.org/2023.ccl-3.25.pdf S&A-CCL2023评测报告.pdf] | ||
| + | ** [http://cuge.baai.ac.cn/#/ccl/2023/cltc 比赛榜单] | ||
| + | |||
| + | * 刘亚慧，李正华，张民. CCL汉语框架语义解析评测(三等奖). 2023年8月. [https://aclanthology.org/2023.ccl-3.9.pdf 官网评测报告.pdf]， [https://tianchi.aliyun.com/competition/entrance/532083/rankingList 比赛榜单] | ||
| + | |||
| − | * 2022.12法研杯第一名 CAIL-2022 | + | * 2022.12法研杯第一名 CAIL-2022 法律文本纠错 |
* 我们组织了两届跨领域句法分析评测：CCL-2021和NLPCC-2019 | * 我们组织了两届跨领域句法分析评测：CCL-2021和NLPCC-2019 | ||
| 第62行： | 第75行： | ||
== Awards == | == Awards == | ||
| + | * 2024. 第三届全国大模型智能生成大会（CIPS-LMG 2024）优秀海报奖（EMNLP-2024论文） | ||
| + | * 2023. CCF-NLPCC“青年新锐学者” （Young Outstanding Scientist Award） | ||
* 2022. SudaNLP团队张宇同学的硕士论文《基于树形条件随机场的高阶句法分析》被评选为2022年度江苏省优秀学术型硕士学位论文 [http://hlt.suda.edu.cn/index.php/Zhangyu-jiangsu-outstanding-paper wechat-sudanlp-news] | * 2022. SudaNLP团队张宇同学的硕士论文《基于树形条件随机场的高阶句法分析》被评选为2022年度江苏省优秀学术型硕士学位论文 [http://hlt.suda.edu.cn/index.php/Zhangyu-jiangsu-outstanding-paper wechat-sudanlp-news] | ||
* 2022. Coling '''best paper''' | * 2022. Coling '''best paper''' | ||
| 第67行： | 第82行： | ||
* 2020. NLPCC best paper | * 2020. NLPCC best paper | ||
| − | == 2023 == | + | |
| + | == 同学必须深入学习的东西 == | ||
| + | |||
| + | [http://hlt.suda.edu.cn/index.php/LA-to-sudy-list LAGroup 同学必须深入学习的东西] 慢慢完善 | ||
| + | |||
| + | |||
| + | == 2026 == | ||
| + | |||
| + | === Papers in English === | ||
| + | |||
| + | * Lijie Wang, Yahui Liu, Yue Zhang, Zhenghua Li*. LLM-assisted Data Quality Improvement: SRL as a Case Study. In Findings of EMNLP 2026, Budapest, Hungary. [[文件:Emnlp-2026-lyh.pdf|pdf]]【待补充offical官网】. | ||
| + | |||
| + | === Papers in Chinese === | ||
| + | * 周昊喆, 李正华*. 面向结构置信度不足：LLM 语义指导的介词短语依附消歧方法. CCL 2026 [[文件:CCL_2026_zhz.pdf|pdf]] | ||
| + | |||
| + | == 2025 == | ||
| + | |||
| + | === Journal/Conference Papers in Chinese === | ||
| + | |||
| + | * [期刊发表后更新下] 严福康, 章岳, 李正华*. 2023. 基于网络词典的现代汉语词义消歧数据集构建. 第二十二届中国计算语言学大会.[[文件:基于网络词典的现代汉语词义消歧数据集构建_CCL_严福康.pdf]] | ||
| + | |||
| + | * [期刊发表后更新下] 杨浩苹, 夏庆荣, 李正华*, 王睿. 基于GCN的异构句法驱动汉语语义角色标注. 计算机应用与软件. [2022年录用] [还未正式发表 知网上找不到，期号卷号未知.] '''以后不投这个期刊了'''. [[文件:基于GCN的异构句法驱动汉语语义角色标注.pdf]] | ||
| + | |||
| + | === Papers in English === | ||
| + | |||
| + | * Yahui Liu, Zhenghua Li, Chen Gong*, Shilin Zhou，Min Zhang. Annotation error detection in painstakingly annotated data: Part-of-speech tagging as a case study. Expert Systems With Applications (ESWA), 2025,290:128374. [https://www.sciencedirect.com/science/article/pii/S0957417425019931 official] [Journal] | ||
| + | |||
| + | * Ziyan Zhang, Yang Hou, Chen Gong*, Zhenghua Li. Self-Correction Makes LLMs Better Parsers. In Findings of EMNLP 2025, Suzhou, China. [https://arxiv.org/abs/2504.14165 Arxiv]. | ||
| + | |||
| + | * Houquan Zhou, Bo Zhang, Zhenghua Li*, Ming Yan, and Min Zhang. 2025. A Training-free LLM-based Approach to General Chinese Character Error Correction. In Proceedings of ACL, pages 13827–13852, Vienna, Austria. Association for Computational Linguistics. [https://aclanthology.org/2025.acl-long.678.pdf official] July 27 - August 1 | ||
| + | * Ziheng Qiao, Houquan Zhou, Zhenghua Li*. Mixture of Small and Large Models for Chinese Spelling Check. ACL, pages 28298–28311, Vienna, Austria. [https://aclanthology.org/2025.acl-long.1372.pdf acl-anthology] | ||
| + | * Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li*, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang. DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check. ACL, pages 28312–28324, Vienna, Austria. [https://aclanthology.org/2025.acl-long.1373.pdf acl-anthology] | ||
| + | * Yang Hou, Zhenghua Li*. Dynamic Head Selection for Neural Lexicalized Constituency Parsing. In Proceedings of ACL 2025, pages 16141–16155, Vienna, Austria. [https://aclanthology.org/2025.acl-long.786.pdf acl-anthology] | ||
| + | * Yang Hou, Zhenghua Li*. Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsing. In Findings of ACL 2025, pages 10701–10713, Vienna, Austria. [https://aclanthology.org/2025.findings-acl.557.pdf acl-anthology] | ||
| + | * Yanggan Gu, Junzhuo Li, Sirui Huang, Xin Zou, Zhenghua Li*, Xuming Hu*. Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models. In Findings of ACL 2025, pages 15959–15973, Vienna, Austria. [https://aclanthology.org/2025.findings-acl.822.pdf acl-anthology] | ||
| + | |||
| + | * Xuebin Wang, Lei Zhang, Zhenghua Li*, Shilin Zhou, Chen Gong, Yang Hou. Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation. [https://arxiv.org/abs/2412.09045 Arxiv]. COLING. January 19–24, 2025. Abu Dhabi, UAE. pages 1247–1257 | ||
| + | * Ziyan Zhang, Yang Hou, Chen Gong*, Zhenghua Li. Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization. [[文件:Data_Augmentation_for_Cross-domain_Parsing_via_Lightweight_LLM_Generation_and_Tree_Hybridization.pdf]]. COLING. 19 January, 2025. Abu Dhabi, UAE. | ||
| + | * Xi Ma, Yang Hou, Xuebin Wang, Zhenghua Li. A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese. [[文件:A_Probabilistic_Toolkit_for_Multi-grained_Word_Segmentation_in_Chinese.pdf]]. COLING Demonstration (demo paper). 19 January, 2025. Abu Dhabi, UAE. | ||
| + | |||
| + | == 2024 == | ||
=== Journal/Conference Papers in Chinese === | === Journal/Conference Papers in Chinese === | ||
| − | + | * 崔秀莲, 严福康, 李正华*. CCKS-2023. 基于实例的词性标注数据错误检测. 2023全国知识图谱与语义计算大会CCKS | |
| − | * 崔秀莲, 严福康, 李正华*. 2023. 基于实例的词性标注数据错误检测. | + | ** 转发：山西大学学报 2024年4月 47卷2期 47(2)，pp251−259. [[文件:Cxl-山西大学学报-基于实例的词性标注数据错误检测.pdf]] |
| − | * | ||
=== Conference Papers in English === | === Conference Papers in English === | ||
| + | * Houquan Zhou, Zhenghua Li*, Bo Zhang, Chen Li, Shaopeng Lai, Ji Zhang, Fei Huang, Min Zhang. 2024. A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models. EMNLP. pp 17446–17467. [https://arxiv.org/abs/2410.04027 arxiv] [https://aclanthology.org/2024.emnlp-main.966.pdf acl-anthology] November 12-16 Miami, Florida (USA) | ||
| − | * | + | * Xuebin Wang, Zhenghua Li*. 2024. Two Sequence Labeling Approaches to Sentence Segmentation and Punctuation Prediction for Classic Chinese Texts. [https://aclanthology.org/2024.lt4hala-1.28/ Acl-anthology] the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024. pages 237–241 25 May, 2024 Torino (Italia) Turin (Italy) |
| − | * | + | * Yumeng Liu, Zhenghua Li*, Haochen Jiang, Bo Zhang, Chen Li, Ji Zhang. 2024. Towards Better Utilization of Multi-Reference Training Data for Chinese Grammatical Error Correction. Findings of ACL. [https://github.com/ymliucs/MrGEC code][https://aclanthology.org/2024.findings-acl.180 paper] |
| + | * Yang Hou and Zhenghua Li*. 2024. Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure. ACL-findings. [[文件:2024.findings-acl.173.pdf]], [[文件:2024.findings-acl.173.slide.pdf]], [[文件:2024.findings-acl.173.poster.pdf]] | ||
| + | * Shilin Zhou, Zhenghua Li, Chen Gong*, Lei Zhang, Yu Hong, Min Zhang. 2024. Chinese Spoken Named Entity Recognition in Real-world Scenarios: Dataset and Approaches. Findings of ACL. [[文件:ACL2024_rwcsner.pdf]]，[[文件:Rwcs_poster.pdf]] | ||
| + | * Shilin Zhou, Zhenghua Li*, Yu Hong, Min Zhang, Zhefeng Wang, Baoxing Huai. 2024. CopyNE: Better Contextual ASR by Copying Named Entities. ACL. [[文件:ACL2024_copyne.pdf]]，[[文件:copyne_poster.pdf]] [https://aclanthology.org/2024.acl-long.147.pdf acl-anthology] Bangkok, Thailand 2024.8.11-16 pp. 2675–2686 | ||
| − | * | + | * Yanggan Gu, Yang Hou, Zhefeng Wang, Xinyu Duan and Zhenghua Li*. 2024. High-order Joint Constituency and Dependency Parsing. COLING. [[文件:2024.lrec-main.713.pdf]]，[[文件:2024.lrec-main.713.poster.pdf]] pages 8144–8154 20-25 May, 2024. Torino (Italia) |
| + | * Chenhui Dou, Chen Gong*, Zhenghua Li, Zhefeng Wang, baoxing Huai and Min Zhang. 2024. Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling. COLING.[[文件:2024.lrec-main.765.pdf]]，[[文件:2024.lrec-main.765.poster.pdf]] pages 8732–8742 | ||
| + | 20-25 May, 2024. Torino (Italia) Turin (Italy) | ||
| − | * Saihao Huang, Lijie Wang, Zhenghua Li*, Zeyang Liu, Chenhui Dou, Fukang Yan, Xinyan Xiao, Hua Wu, and Min Zhang. 2023. SeSQL: A High-Quality Large-Scale Session-Level Chinese Text-to-SQL Dataset. NLPCC 2023, pages 537-550.[[文件:SeSQL_A_High-Quality_Large-Scale_Session-Level_Chinese_Text-to-SQL_Dataset.pdf]] | + | == 2023 == |
| + | |||
| + | === Conference Papers in English === | ||
| + | |||
| + | |||
| + | * Houquan Zhou, Yumeng Liu, Zhenghua Li*, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang. 2023. Improving Seq2Seq Grammatical Error Correction via Decoding Interventions. Findings of '''EMNLP''', pages 7393–7405. [https://arxiv.org/abs/2310.14534 arxiv][https://github.com/Jacob-Zhou/gecdi code][https://www.semanticscholar.org/paper/Improving-Seq2Seq-Grammatical-Error-Correction-via-Zhou-Liu/4711f26c0295fed15161b6145800b3df1ab9c0f6 citation] | ||
| + | |||
| + | * Yue Zhang, Leyang Cui, Enbo Zhao, Wei Bi, Shuming Shi. 2023. RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation. EMNLP 2023.[https://arxiv.org/pdf/2310.07299.pdf arxiv] [https://github.com/hillzhang1999/RobustGEC code] pages 16780–16793; December 6-10, 2023 | ||
| + | |||
| + | * Saihao Huang, Lijie Wang, Zhenghua Li*, Zeyang Liu, Chenhui Dou, Fukang Yan, Xinyan Xiao, Hua Wu, and Min Zhang. 2023. SeSQL: A High-Quality Large-Scale Session-Level Chinese Text-to-SQL Dataset. NLPCC 2023, pages 537-550.[[文件:SeSQL_A_High-Quality_Large-Scale_Session-Level_Chinese_Text-to-SQL_Dataset.pdf]] [https://arxiv.org/abs/2208.12711 arxiv] | ||
| + | |||
| + | * Yue Zhang, Bo Zhang, Haochen Jiang, Zhenghua Li*, Chen Li, Fei Huang, Min Zhang. 2023. NaSGEC: Multi-Domain Chinese Grammatical Error Correction for Native Speaker Texts. Findings of ACL 2023. pp 9935-9951. [https://aclanthology.org/2023.findings-acl.630.pdf official] [https://arxiv.org/pdf/2305.16023.pdf arxiv] [https://github.com/HillZhang1999/NaSGEC code] | ||
== 2022 == | == 2022 == | ||
| 第103行： | 第174行： | ||
=== Conference Papers In English === | === Conference Papers In English === | ||
| − | |||
* Yue Zhang, Bo Zhang, Zhenghua Li*, Zuyi Bao, Chen Li, and Min Zhang. 2022. SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser. In '''EMNLP''', pages 2518–2531. [https://arxiv.org/pdf/2210.12484 arxiv][https://aclanthology.org/2022.emnlp-main.162.pdf official pdf][https://underline.io/events/342/sessions/13833/lecture/66146-syngec-syntax-enhanced-grammatical-error-correction-with-a-tailored-gec-oriented-parser video] | * Yue Zhang, Bo Zhang, Zhenghua Li*, Zuyi Bao, Chen Li, and Min Zhang. 2022. SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser. In '''EMNLP''', pages 2518–2531. [https://arxiv.org/pdf/2210.12484 arxiv][https://aclanthology.org/2022.emnlp-main.162.pdf official pdf][https://underline.io/events/342/sessions/13833/lecture/66146-syngec-syntax-enhanced-grammatical-error-correction-with-a-tailored-gec-oriented-parser video] | ||
* Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu*, Min Zhang. 2022. Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments. In '''COLING''', pages 4212–4227. [https://arxiv.org/abs/2110.06865 arxiv] [https://aclanthology.org/2022.coling-1.370/ official pdf] [https://underline.io/events/360/posters/13239/poster/60359-semantic-role-labeling-as-dependency-parsing-exploring-latent-tree-structures-inside-arguments video] | * Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu*, Min Zhang. 2022. Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments. In '''COLING''', pages 4212–4227. [https://arxiv.org/abs/2110.06865 arxiv] [https://aclanthology.org/2022.coling-1.370/ official pdf] [https://underline.io/events/360/posters/13239/poster/60359-semantic-role-labeling-as-dependency-parsing-exploring-latent-tree-structures-inside-arguments video] | ||
| 第136行： | 第206行： | ||
* 陆凯华, 李正华, 张民. 2020. 汉语上下位关系分类数据集构建和基准方法比较. 厦门大学学报(自然科学版). 2020, 59 (06): 1004-1010 [[文件:汉语上下位关系分类数据集构建和基准方法比较_陆凯华.pdf]] | * 陆凯华, 李正华, 张民. 2020. 汉语上下位关系分类数据集构建和基准方法比较. 厦门大学学报(自然科学版). 2020, 59 (06): 1004-1010 [[文件:汉语上下位关系分类数据集构建和基准方法比较_陆凯华.pdf]] | ||
| + | * 刘亚慧, 杨浩苹, 李正华, 张民. 2020. 一种轻量级的语义角色标注规范. 中文信息学报. 2020, 34(4):10-20 [http://jcip.cipsc.org.cn/CN/Y2020/V34/I4/10 offical.pdf] | ||
=== Journal Papers In English=== | === Journal Papers In English=== | ||
| 第164行： | 第235行： | ||
* Meishan Zhang, Zhenghua Li, Guohong Fu and Min Zhang. Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations. In Proceedings of the NAACL-2019. pp. 1151–1161. Seattle, America, 5-10 Jun. 2019. [https://www.aclweb.org/anthology/N19-1118.pdf pdf] | * Meishan Zhang, Zhenghua Li, Guohong Fu and Min Zhang. Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations. In Proceedings of the NAACL-2019. pp. 1151–1161. Seattle, America, 5-10 Jun. 2019. [https://www.aclweb.org/anthology/N19-1118.pdf pdf] | ||
* Bowen Wu, Jiayuan Chao, Baoxun Wang, Zhenghua Li and Min Zhang. Abstractive Summarization via Continuous Copy. EMNLP-2019 Workshop Summarization Submission. Aug 20, 2019. (not accepted) | * Bowen Wu, Jiayuan Chao, Baoxun Wang, Zhenghua Li and Min Zhang. Abstractive Summarization via Continuous Copy. EMNLP-2019 Workshop Summarization Submission. Aug 20, 2019. (not accepted) | ||
| + | |||
| + | [http://hlt.suda.edu.cn/~zhli/en.html <font color="#FF0000"><b>更早的论文，请点击此</b></font>] | ||
== 202? Template == | == 202? Template == | ||
2026年10月20日 (二) 03:40的最新版本
请大家按照规则不断完善此页面。包含pdf ppt codes等。论文按年度，先中文、再英文；先期刊、再会议；先录用时间、后发表（开会）时间。尽量用英文吧。
文献格式和内容与内部wiki保持一致（尽量避免重复劳动）
- pdf ppt等附件都可以放到外网可以访问的地方，放一个地方，避免重复
- 基金号等信息，这个页面上删掉，不要写
bib and abstract
摘要和基金信息请看内部wiki
Talks（报告）
- 视频尽可能都放在了哔哩哔哩上了（搜用户名：LAGroup）
- 2024年11月24日受南师大李斌老师邀请做报告（大模型时代如何做研究：一些思考）【文本纠错任务上的大模型相关工作，作为例子】
- 2024年2月1日受邀参加2024阿里云高校前沿技术论坛（大模型时代下文本校对研究的尝试和构想）【小而美的研究工作】
- 2023年4月8日受北语杨天麟老师邀请做报告（大模型时代句法语义研究何去何从）
- 2022年11月29日受复旦邱锡鹏老师邀请做报告（基于适配句法知识的文本纠错）
- 2022年11月11日受邀对COLING-2022 Best Paper做英文报告【按邀请顺序：新加坡国立大学、新加坡设计与技术大学、南京大学】
- 2022年8月27日，受邀在江苏省人工智能大会上做报告（汉语文本纠错近年进展：数据集和模型）
- 2021.7.27：《数据标注师资培训》(哈工大大数据集团)
- 2021.4.20：《基于树形条件随机场的句法分析》(CCF-NLP走进高校-西湖大学)
- 2020.10：《神经网络》慕课 - 面向自然语言处理的神经网络 （13章）
- 2020.8.15: I have given a talk on data annotation at AI+EDUCATION SUB-FORUM at AI-EXPO (2020 GLOBAL AI PRODUCT AND APPLICATION EXPO)
- 周厚全，乔子恒，蒋浩辰，刘雨萌. 金山办公2024算法挑战赛-中文文本智能校对大赛，第一名，一等奖
- 刘亚慧、龚晨、张民. 2024.8. CCL-2024 第二届汉语框架语义解析（开放赛道）, 一等奖 官方评测报告.pdf ， 比赛榜单
- 王学彬, 李正华. 2024.5. 第一届古汉语断句标点评测（EvaHan2024）评测，二等奖*（COLING-2024 workshop）
- 辜仰淦，周仕林，李正华. 2023年8月. CCL中文抽象语义表示解析评测（一等奖）官网评测报告
- 蒋浩辰，刘雨萌，周厚全，乔子恒，章波，李辰，李正华，张民. CCL汉语学习者文本纠错评测（封闭、开放双赛道第一）. 2023年8月. S&A-CCL2023评测报告.pdf
- 刘亚慧，李正华，张民. CCL汉语框架语义解析评测(三等奖). 2023年8月. 官网评测报告.pdf， 比赛榜单
- 2022.12法研杯第一名 CAIL-2022 法律文本纠错
- 我们组织了两届跨领域句法分析评测：CCL-2021和NLPCC-2019
- 李嘉诚，沈嘉钰，包祖贻，章波，章岳，李辰，李正华. S&A团队CGED-7评测报告（识别，定位，纠正层第一）. 2021年12月. 文件:S&A团队CGED-7评测报告.pdf
- 章岳，包祖贻，章波，李辰，李嘉诚，李正华. S&A队CTC2021评测报告（检错、纠错、总分三赛道第一）. 2021年9月.文件:S&A-CTC2021评测报告.pdf
Awards
- 2024. 第三届全国大模型智能生成大会（CIPS-LMG 2024）优秀海报奖（EMNLP-2024论文）
- 2023. CCF-NLPCC“青年新锐学者” （Young Outstanding Scientist Award）
- 2022. SudaNLP团队张宇同学的硕士论文《基于树形条件随机场的高阶句法分析》被评选为2022年度江苏省优秀学术型硕士学位论文 wechat-sudanlp-news
- 2022. Coling best paper
- 2021. 章波，江苏省优秀学术型硕士论文；同时获江苏省计算机学会优秀硕士论文《面向依存句法的树库转化与应用研究》
- 2020. NLPCC best paper
同学必须深入学习的东西
LAGroup 同学必须深入学习的东西 慢慢完善
2026
Papers in English
- Lijie Wang, Yahui Liu, Yue Zhang, Zhenghua Li*. LLM-assisted Data Quality Improvement: SRL as a Case Study. In Findings of EMNLP 2026, Budapest, Hungary. 文件:Emnlp-2026-lyh.pdf【待补充offical官网】.
Papers in Chinese
- 周昊喆, 李正华*. 面向结构置信度不足：LLM 语义指导的介词短语依附消歧方法. CCL 2026 文件:CCL 2026 zhz.pdf
2025
Journal/Conference Papers in Chinese
- [期刊发表后更新下] 严福康, 章岳, 李正华*. 2023. 基于网络词典的现代汉语词义消歧数据集构建. 第二十二届中国计算语言学大会.文件:基于网络词典的现代汉语词义消歧数据集构建 CCL 严福康.pdf
- [期刊发表后更新下] 杨浩苹, 夏庆荣, 李正华*, 王睿. 基于GCN的异构句法驱动汉语语义角色标注. 计算机应用与软件. [2022年录用] [还未正式发表 知网上找不到，期号卷号未知.] 以后不投这个期刊了. 文件:基于GCN的异构句法驱动汉语语义角色标注.pdf
Papers in English
- Yahui Liu, Zhenghua Li, Chen Gong*, Shilin Zhou，Min Zhang. Annotation error detection in painstakingly annotated data: Part-of-speech tagging as a case study. Expert Systems With Applications (ESWA), 2025,290:128374. official [Journal]
- Ziyan Zhang, Yang Hou, Chen Gong*, Zhenghua Li. Self-Correction Makes LLMs Better Parsers. In Findings of EMNLP 2025, Suzhou, China. Arxiv.
- Houquan Zhou, Bo Zhang, Zhenghua Li*, Ming Yan, and Min Zhang. 2025. A Training-free LLM-based Approach to General Chinese Character Error Correction. In Proceedings of ACL, pages 13827–13852, Vienna, Austria. Association for Computational Linguistics. official July 27 - August 1
- Ziheng Qiao, Houquan Zhou, Zhenghua Li*. Mixture of Small and Large Models for Chinese Spelling Check. ACL, pages 28298–28311, Vienna, Austria. acl-anthology
- Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li*, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang. DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check. ACL, pages 28312–28324, Vienna, Austria. acl-anthology
- Yang Hou, Zhenghua Li*. Dynamic Head Selection for Neural Lexicalized Constituency Parsing. In Proceedings of ACL 2025, pages 16141–16155, Vienna, Austria. acl-anthology
- Yang Hou, Zhenghua Li*. Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsing. In Findings of ACL 2025, pages 10701–10713, Vienna, Austria. acl-anthology
- Yanggan Gu, Junzhuo Li, Sirui Huang, Xin Zou, Zhenghua Li*, Xuming Hu*. Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models. In Findings of ACL 2025, pages 15959–15973, Vienna, Austria. acl-anthology
- Xuebin Wang, Lei Zhang, Zhenghua Li*, Shilin Zhou, Chen Gong, Yang Hou. Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation. Arxiv. COLING. January 19–24, 2025. Abu Dhabi, UAE. pages 1247–1257
- Ziyan Zhang, Yang Hou, Chen Gong*, Zhenghua Li. Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization. 文件:Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization.pdf. COLING. 19 January, 2025. Abu Dhabi, UAE.
- Xi Ma, Yang Hou, Xuebin Wang, Zhenghua Li. A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese. 文件:A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese.pdf. COLING Demonstration (demo paper). 19 January, 2025. Abu Dhabi, UAE.
2024
Journal/Conference Papers in Chinese
- 崔秀莲, 严福康, 李正华*. CCKS-2023. 基于实例的词性标注数据错误检测. 2023全国知识图谱与语义计算大会CCKS
- 转发：山西大学学报 2024年4月 47卷2期 47(2)，pp251−259. 文件:Cxl-山西大学学报-基于实例的词性标注数据错误检测.pdf
Conference Papers in English
- Houquan Zhou, Zhenghua Li*, Bo Zhang, Chen Li, Shaopeng Lai, Ji Zhang, Fei Huang, Min Zhang. 2024. A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models. EMNLP. pp 17446–17467. arxiv acl-anthology November 12-16 Miami, Florida (USA)
- Xuebin Wang, Zhenghua Li*. 2024. Two Sequence Labeling Approaches to Sentence Segmentation and Punctuation Prediction for Classic Chinese Texts. Acl-anthology the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024. pages 237–241 25 May, 2024 Torino (Italia) Turin (Italy)
- Yumeng Liu, Zhenghua Li*, Haochen Jiang, Bo Zhang, Chen Li, Ji Zhang. 2024. Towards Better Utilization of Multi-Reference Training Data for Chinese Grammatical Error Correction. Findings of ACL. codepaper
- Yang Hou and Zhenghua Li*. 2024. Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure. ACL-findings. 文件:2024.findings-acl.173.pdf, 文件:2024.findings-acl.173.slide.pdf, 文件:2024.findings-acl.173.poster.pdf
- Shilin Zhou, Zhenghua Li, Chen Gong*, Lei Zhang, Yu Hong, Min Zhang. 2024. Chinese Spoken Named Entity Recognition in Real-world Scenarios: Dataset and Approaches. Findings of ACL. 文件:ACL2024 rwcsner.pdf，文件:Rwcs poster.pdf
- Shilin Zhou, Zhenghua Li*, Yu Hong, Min Zhang, Zhefeng Wang, Baoxing Huai. 2024. CopyNE: Better Contextual ASR by Copying Named Entities. ACL. 文件:ACL2024 copyne.pdf，文件:Copyne poster.pdf acl-anthology Bangkok, Thailand 2024.8.11-16 pp. 2675–2686
- Yanggan Gu, Yang Hou, Zhefeng Wang, Xinyu Duan and Zhenghua Li*. 2024. High-order Joint Constituency and Dependency Parsing. COLING. 文件:2024.lrec-main.713.pdf，文件:2024.lrec-main.713.poster.pdf pages 8144–8154 20-25 May, 2024. Torino (Italia)
- Chenhui Dou, Chen Gong*, Zhenghua Li, Zhefeng Wang, baoxing Huai and Min Zhang. 2024. Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling. COLING.文件:2024.lrec-main.765.pdf，文件:2024.lrec-main.765.poster.pdf pages 8732–8742
20-25 May, 2024. Torino (Italia) Turin (Italy)
2023
Conference Papers in English
- Houquan Zhou, Yumeng Liu, Zhenghua Li*, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang. 2023. Improving Seq2Seq Grammatical Error Correction via Decoding Interventions. Findings of EMNLP, pages 7393–7405. arxivcodecitation
- Yue Zhang, Leyang Cui, Enbo Zhao, Wei Bi, Shuming Shi. 2023. RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation. EMNLP 2023.arxiv code pages 16780–16793; December 6-10, 2023
- Saihao Huang, Lijie Wang, Zhenghua Li*, Zeyang Liu, Chenhui Dou, Fukang Yan, Xinyan Xiao, Hua Wu, and Min Zhang. 2023. SeSQL: A High-Quality Large-Scale Session-Level Chinese Text-to-SQL Dataset. NLPCC 2023, pages 537-550.文件:SeSQL A High-Quality Large-Scale Session-Level Chinese Text-to-SQL Dataset.pdf arxiv
- Yue Zhang, Bo Zhang, Haochen Jiang, Zhenghua Li*, Chen Li, Fei Huang, Min Zhang. 2023. NaSGEC: Multi-Domain Chinese Grammatical Error Correction for Native Speaker Texts. Findings of ACL 2023. pp 9935-9951. official arxiv code
2022
Journal/Conference Papers in Chinese
- 章岳, 黄赛豪, 陆凯华, 李正华*. 2022年1月. 基于模板的中文上下位关系抽取方法. 计算机应用与软件: 39卷1期 pp126-134. 文件:Hypernym-zhangyue-2022.pdf
- 周仕林, 龚晨*, 李正华, 张民. 基于转移的快速精准的语义依存图分析. 山西大学学报(自然科学版): 45卷4期 pp1-13. 文件:Slzhou transition based sdp.pdf
- 李帅克，李英，李正华*，张民. 基于tri-training的跨领域依存句法分析. 厦门大学学报（自然科学版）：61卷4期 pp638-645. [知网抢先版链接]文件:基于tri-training的跨领域依存句法分析 李帅克.pdf
- 周明月，龚晨，李正华*，张民. 2022.数据标注方法比较研究：以依存句法树标注为例. 清华大学学报（自然科学版）：62卷5期 pp908-916. [电子版] 文件:数据标注方法比较研究.pdf
- 彭雪, 李正华*, 张民. 2022. 基于语言模型微调的跨领域依存句法分析. 计算机应用与软件:39卷07期, pp141-146. 文件:彭雪-基于语言模型微调的跨领域依存句法分析.pdf
- 李嘉诚, 沈嘉钰, 龚 晨, 李正华*, 张 民. 2022. 基于指针网络融入混淆集知识的中文语法纠错 中文信息学报:36卷04期,pp29-38. 文件:基于指针网络融入混淆集知识的中文语法纠错.pdf
Journal Papers in English
- Chen Gong, Zhenghua Li* and Min Zhang. Neural Coupled Sequence Labeling for Heterogeneous Annotation Conversion. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30:1624-1636.official
Conference Papers In English
- Yue Zhang, Bo Zhang, Zhenghua Li*, Zuyi Bao, Chen Li, and Min Zhang. 2022. SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser. In EMNLP, pages 2518–2531. arxivofficial pdfvideo
- Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu*, Min Zhang. 2022. Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments. In COLING, pages 4212–4227. arxiv official pdf video
- Shilin Zhou, Qingrong Xia, Zhenghua Li*, Yu Zhang, Yu Hong, and Min Zhang. 2022. Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing. In COLING, pages 4160–4171. arxiv official pdf video (best paper!)
- Yahui Liu, Haoping Yang, Chen Gong*, Qingrong Xia, Zhenghua Li, Min Zhang. 2022. MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset. In NAACL, pages 1707-1717. arxivofficial pdfvideo
- Yue Zhang, Zhenghua Li*, Zuyi Bao, Jiacheng Li, Bo Zhang, Chen Li, Fei Huang, Min Zhang. 2022. MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction. In NAACL, pages 3118–3130. arxivofficial pdfvideo
- Ying Li, Shuaike Li, Min Zhang. 2022. Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network. In 'ACL 2022, pages 1035--1045. official-pdf camera ready pdf video.
- Houquan Zhou, Yang Li, Zhenghua Li, and Min Zhang. 2022. Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3276–3290, Dublin, Ireland. Association for Computational Linguistics. pdf camera ready pdf official pdf video
2021
Journal/Conference Papers in Chinese
- 吴锟，周夏冰，李正华，梁兴伟，陈文亮. 中文知识库问答中的路径选择. 中文信息学报（CCKS会议推荐）. 2021, 35(9):113-122.文件:中文知识库问答中的路径选择 吴锟.pdf
Conference Papers In English
- Yang Hou, Houquan Zhou, Zhenghua Li*, Yu Zhang, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan. A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing. Proceedings of CoNLL-2021, pp. 290–299. Punta Cana, Dominican Republic (Online), 10-11 Nov. 2021. 文件:CoNLL 2021 yhou official version.pdf
- Kun Wu, Lijie Wang, Zhenghua Li, Ao Zhang, Xinyan Xiao, Hua Wu, Min Zhang, Haifeng Wang. Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-Domain Text-to-SQL Parsing. Proceedings of EMNLP-2021, pp. 8974--8983. Punta Cana, Dominican Republic (Online), 7-11 Nov. 2021. 文件:EMNLP2021 camera ready Data Augmentation with Hierarchical SQL to Question Generation forCross domain Text to SQL Parsing-09101500.pdf
- Qingrong Xia, Zhenghua Li*, Rui Wang, Min Zhang. Stacked AMR Parsing with Silver Data. Proceedings of EMNLP-2021 Findings, pp. 4729--4738. Punta Cana, Dominican Republic (Online), 7-11 Nov. 2021. 文件:EMNLP 2021 Stacked AMR Parsing with Silver Data.pdf
- Ying Li, Meishan Zhang, Zhenghua Li*, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan. APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing. Proceedings of EMNLP-2021 Findings, pp. 1727–1733. Punta Cana, Dominican Republic (Online), 7-11 Nov. 2021. 文件:EMNLP 2021 yli camera ready.pdf
- Chen Gong, Saihao Huang, Houquan Zhou, Zhenghua Li*, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan. An In-depth Study on Internal Structure of Chinese Words. Proceedings of ACL-2021, pp. 5823–5833. Online, Virtual Event, 1-6 Aug. 2021. 文件:2021.acl-long.452.pdf
- Qingrong Xia, Bo Zhang, Rui Wang, Zhenghua Li*, Yue Zhang, Fei Huang, Luo Si, Min Zhang. 2021. A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents. Proceedings of NAACL-2021, pp. 1795-1804. Mexico City, Mexico (Online), 6-11 June. 2021. 文件:2021.naacl-main.144.pdf
2020
Journal Papers in Chinese
- 陆凯华, 李正华, 张民. 2020. 汉语上下位关系分类数据集构建和基准方法比较. 厦门大学学报(自然科学版). 2020, 59 (06): 1004-1010 文件:汉语上下位关系分类数据集构建和基准方法比较 陆凯华.pdf
- 刘亚慧, 杨浩苹, 李正华, 张民. 2020. 一种轻量级的语义角色标注规范. 中文信息学报. 2020, 34(4):10-20 offical.pdf
Journal Papers In English
- Chen Gong, Zhenghua Li, Qingrong Xia, Wenliang Chen and Min Zhang. Hierarchical LSTM with char-subword-word tree-structure representation for Chinese named entity recognition. Science China Information Science, 2020, 63(10):1-15. 文件:Hierarchical LSTM with char-subword-word tree-structure representation for Chinese named entity recognition.pdf
Conference Papers In English
- Ying Li, Zhenghua Li* and Min Zhang. Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations. Proceedings of COLING-2020. pp. 3806–3817. Barcelona, Spain (Online), 8-13 Dec. 2020.pdf 文件:Liying-2020.coling-main.338.pdf
- Qingrong Xia, Rui Wang, Zhenghua Li, Yue Zhang and Min Zhang*. Semantic Role Labeling with Heterogeneous Syntactic Knowledge. Proceedings of COLING-2020. pp. 2979-2990. Barcelona, Spain (Online), 8-13 Dec. 2020. (pdf)(文件:Xiaqingrong-2020.coling-main.266.pdf)(文件:Poster-SRL-HDP.pdf)(文件:SRL-HDP.pptx)
- Chen Gong, Zhenghua Li*, Bowei Zou and Min Zhang. Multi-grained Chinese Word Segmentation with Weakly Labeled Data. Proceedings of COLING-2020. pp. 2026–2036. Barcelona, Spain (Online), 8-13 Dec. 2020. pdf文件:Gongchen-2020.coling-main.183.pdf
- Lijie Wang, Ao Zhang, Kun Wu, Ke Sun, Zhenghua Li, Hua Wu, Min Zhang and Haifeng Wang. DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset. Proceedings of EMNLP-2020. pp. 6923-6935. Online, 16-20 Nov. 2020. pdf文件:2020.emnlp-main.562.pdf
- Houquan Zhou, Yu Zhang, Zhenghua Li, and Min Zhang. Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing? Proceedings of NLPCC-2020, pp. 179--191. Zhengzhou, China, 14 Oct. - 18 Oct. 2020. (pdf) (pdf-official) (pdf-official-w-content) (best paper!)
- Yu Zhao, Mingyue Zhou, Zhenghua Li, and Min Zhang. Dependency Parsing with Noisy Multi-Annotation Data. Proceedings of NLPCC-2020, pp. 120-131. Zhengzhou, China, 14 Oct. - 18 Oct. 2020. (pdf）(pdf-official) (pdf-official-w-content)
- Yu Zhang, Houquan Zhou, Zhenghua Li. 2020. Fast and Accurate Neural CRF Constituency Parsing. Proceedings of IJCAI-2020, pp. 4046-4053. Yokohama, Japan, 11-17 Jul. 2020. pdf-official pdf [video(5 min version)] [video(10 min version)] [video(15 min version)]
- Yu Zhang, Zhenghua Li, Min Zhang. 2020. Efficient Second-Order TreeCRF for Neural Dependency Parsing. Proceedings of ACL-2020, pp. 3295-3305. Seattle, America, 5-10 Jul. 2020. [pdf-official] [pdf] [video]
- A very good paper: Timothy Dozat, Christopher D. Manning. ICLR-2017. Deep Biaffine Attention for Neural Dependency Parsing. arxiv
- Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang. Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks. Proceedings of ACL-2020, pp. 3249-3258. Seattle, America, 5-10 Jul. 2020. pdf 文件:Zhangbo-acl2020-ppt-5-24.pdf
before 2020
- Meishan Zhang, Zhenghua Li, Guohong Fu and Min Zhang. Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations. In Proceedings of the NAACL-2019. pp. 1151–1161. Seattle, America, 5-10 Jun. 2019. pdf
- Bowen Wu, Jiayuan Chao, Baoxun Wang, Zhenghua Li and Min Zhang. Abstractive Summarization via Continuous Copy. EMNLP-2019 Workshop Summarization Submission. Aug 20, 2019. (not accepted)