Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Resume - He Pan</title> | |
| <link rel="stylesheet" href="style.css"> | |
| <script src="https://cdn.tailwindcss.com"></script> | |
| <script src="https://cdn.jsdelivr.net/npm/feather-icons/dist/feather.min.js"></script> | |
| <script src="https://unpkg.com/feather-icons"></script> | |
| <script src="components/resume-header.js"></script> | |
| <script src="components/resume-section.js"></script> | |
| <script src="components/resume-footer.js"></script> | |
| </head> | |
| <body class="bg-gray-50 text-gray-800 font-sans"> | |
| <div class="max-w-4xl mx-auto p-6 md:p-8"> | |
| <resume-header></resume-header> | |
| <main class="mt-8 space-y-8" id="resume-content"> | |
| <!-- Resume content will be dynamically loaded here --> | |
| </main> | |
| <resume-footer></resume-footer> | |
| </div> | |
| <script> | |
| feather.replace(); | |
| // Load resume data from JSON file | |
| fetch('resume.json') | |
| .then(response => response.json()) | |
| .then(data => { | |
| const resumeContent = document.getElementById('resume-content'); | |
| generateResumeContent(data, resumeContent); | |
| feather.replace(); // Refresh icons after content is loaded | |
| }) | |
| .catch(error => { | |
| console.error('Error loading resume data:', error); | |
| }); | |
| </script> | |
| <div class="space-y-6"> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <div class="flex justify-between items-start"> | |
| <div> | |
| <h3 class="text-lg font-semibold">电子科技大学</h3> | |
| <p class="text-gray-600">计算机科学与技术 - 硕士</p> | |
| </div> | |
| <span class="text-gray-500">2020-09 - 至今</span> | |
| </div> | |
| <div class="mt-2"> | |
| <p class="text-gray-700"><span class="font-medium">GPA:</span> 4.4(示例)</p> | |
| <p class="text-gray-700 mt-1"><span class="font-medium">Courses:</span> 自然语言处理, 深度学习, 机器学习, 计算机操作系统, 计算机网络</p> | |
| </div> | |
| </div> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <div class="flex justify-between items-start"> | |
| <div> | |
| <h3 class="text-lg font-semibold">吉林大学</h3> | |
| <p class="text-gray-600">地球物理 - 学士</p> | |
| </div> | |
| <span class="text-gray-500">2016-09 - 2020-06</span> | |
| </div> | |
| <div class="mt-2"> | |
| <p class="text-gray-700"><span class="font-medium">GPA:</span> 4.4/5.0</p> | |
| <p class="text-gray-700 mt-1"><span class="font-medium">Courses:</span> 计算机操作系统, 计算机网络, 自然语言处理基础, 机器学习导论, 深度学习框架实践</p> | |
| </div> | |
| </div> | |
| </div> | |
| </resume-section> | |
| <resume-section title="Work Experience" icon="briefcase"> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <div class="flex justify-between items-start"> | |
| <div> | |
| <h3 class="text-lg font-semibold">网易伏羲</h3> | |
| <p class="text-gray-600">NLP研究员</p> | |
| </div> | |
| <span class="text-gray-500">2022-03 - 2022-06</span> | |
| </div> | |
| <ul class="mt-4 space-y-3 list-disc list-inside text-gray-700"> | |
| <li>构建基于预训练模型的无监督段落级文本摘要系统，针对游戏剧情生成场景设计创新性数据增强方案。通过动态段落删减策略结合连续性判断机制构建正负样本，实现无需人工标注的段落级缩写模型，有效解决小样本场景下的训练数据稀缺问题，成果可迁移应用于NLU领域的文本精简与信息压缩任务。</li> | |
| <li>主导开发Lizards-GEAT：参数高效且泛化增强的Prompt Tuning框架。创新性提出无梯度反向传播的直接分类架构，显著提升训练效率；设计答案词干扰增强策略，通过错误词注入提升模型泛化能力。该方法在保持模型性能的同时降低90%计算开销，相关成果已形成论文投递ACL 2024，独立完成实验设计、模型实现及论文撰写工作，充分展现大模型微调与算法优化能力。</li> | |
| </ul> | |
| </div> | |
| </resume-section> | |
| <resume-section title="Research Publications" icon="file-text"> | |
| <div class="space-y-6"> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <h3 class="text-lg font-semibold">Sentence Rewriting for Fine-Tuned Model Based on Dictionary: Taking the Track 1 of NLPCC 2021 Argumentative Text Understanding for AI Debater as an Example</h3> | |
| <p class="text-gray-600 mt-1">He P, Wang Y, Zhang Y | CCF International Conference on Natural Language Processing and Chinese Computing | 2021</p> | |
| <p class="text-gray-700 mt-2">Proposed a novel sentence rewriting framework for fine-tuned models based on dictionary matching mechanisms. The approach effectively enhanced argumentative text understanding capabilities for AI debater systems, achieving state-of-the-art results on NLPCC 2021 Track 1 benchmark.</p> | |
| </div> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <h3 class="text-lg font-semibold">Zhegu@SMM4H-2022: The Pre-training Tweet & Claim Matching Makes Your Prediction Better</h3> | |
| <p class="text-gray-600 mt-1">Pan He, Yuze Chen, Yanru Zhang | Proceedings of the Seventh Social Media Mining for Health Applications (SMM4H) Workshop & Shared Task | 2022</p> | |
| <p class="text-gray-700 mt-2">Proposed a pre-training framework for tweet and claim matching in health domain, achieving state-of-the-art accuracy on social media text classification. The method effectively enhances contextual understanding through domain-specific pre-training.</p> | |
| </div> | |
| </div> | |
| </resume-section> | |
| <resume-section title="Skills" icon="code"> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <ul class="space-y-3 list-disc list-inside text-gray-700"> | |
| <li>精通Python编程及PyTorch深度学习框架，具备NLP算法开发经验。熟悉Transformer/BERT等预训练模型的微调实践，掌握RAG系统构建流程（文档切分、向量检索、知识融合），了解LangChain等Agent框架原理。具备模型工程化部署能力，熟悉意图识别、实体抽取等NLU核心任务的优化方法</li> | |
| <li>精通自然语言处理核心技术，包括文本分类、意图识别、实体抽取及情感分析等NLU任务。具备大语言模型（如Llama、GLM）的预训练、微调及Prompt Tuning实践经验，能针对业务场景优化模型效果。熟悉向量数据库和语义检索技术，具备RAG系统全链路开发能力。</li> | |
| <li>CET-6，具备专业级英文听说读写能力，能够高效阅读NLP领域顶会论文（如ACL/EMNLP）并撰写英文学术论文。擅长解析NLU算法论文（意图识别/实体抽取），可快速复现SOTA模型。熟悉Agent领域核心论文（ReAct/Tool-use），具备基于LangChain/LlamaIndex框架的工程实现能力</li> | |
| </ul> | |
| </div> | |
| </resume-section> | |
| <resume-section title="Patents" icon="award"> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <h3 class="text-lg font-semibold">基于预训练模型语义理解的多语言缩写消歧义算法</h3> | |
| <p class="text-gray-600 mt-1">Owner: 何攀</p> | |
| </div> | |
| </resume-section> | |
| <resume-section title="Awards" icon="star"> | |
| <div class="grid grid-cols-1 md:grid-cols-2 gap-4"> | |
| <div class="bg-white p-4 rounded-lg shadow-sm border border-gray-100"> | |
| <h4 class="font-medium">国家励志奖学金</h4> | |
| <p class="text-gray-600 text-sm mt-1">2017-09</p> | |
| </div> | |
| <div class="bg-white p-4 rounded-lg shadow-sm border border-gray-100"> | |
| <h4 class="font-medium">校一等奖学金</h4> | |
| <p class="text-gray-600 text-sm mt-1">2022-09</p> | |
| </div> | |
| <div class="bg-white p-4 rounded-lg shadow-sm border border-gray-100"> | |
| <h4 class="font-medium">校二等奖学金</h4> | |
| <p class="text-gray-600 text-sm mt-1">2021-09</p> | |
| </div> | |
| <div class="bg-white p-4 rounded-lg shadow-sm border border-gray-100"> | |
| <h4 class="font-medium">校三等奖学金</h4> | |
| <p class="text-gray-600 text-sm mt-1">2017-09, 2020-09</p> | |
| </div> | |
| </div> | |
| </resume-section> | |
| <resume-section title="Self Assessment" icon="user"> | |
| <div class="bg-white p-6 rounded-lg shadow-sm border border-gray-100"> | |
| <p class="text-gray-700">具备扎实的自然语言处理理论基础，擅长意图识别、实体抽取等NLU核心技术研发。熟悉Transformer架构及大语言模型微调技术，有基于LangChain框架的智能体开发经验。擅长将前沿研究成果（如ReAct框架）转化为实际业务方案，在多轮对话管理和RAG系统优化方面有成功落地案例。具备优秀的跨团队协作能力，能够通过技术分享促进团队知识沉淀，曾主导构建NLP模型评测体系并推动数据闭环建设。</p> | |
| </div> | |
| </resume-section> | |
| </main> | |
| <script src="https://huggingface.co/deepsite/deepsite-badge.js"></script> | |
| </body> | |
| </html> |