1.EMNLP 2023 信息抽取（NER、码解RE、码解EE）文章列表
2.MongoDB初学快速入门
EMNLP 2023 信息抽取（NER、码解RE、码解EE）文章列表
EMNLP文章列表如下： NER（命名实体识别）2INER: 稀少样本条件下具有指导性和上下文学习的码解命名实体识别
Structure and Label Constrained Data Augmentation for Cross-domain Few-shot NER
Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching
ScdNER: 基于一致性感知的文档级命名实体识别
Towards Building More Robust NER datasets: An Empirical Study on NER Dataset Bias from a Dataset Difficulty View
Continual Named Entity Recognition without Catastrophic Forgetting
Adversarial Robustness for Large Language NER models using Disentanglement and Word Attributions
ESPVR: 多模态命名实体识别中的实体跨度位置视觉区域
CleanCoNLL: 几乎无噪声的命名实体识别数据集
NERetrieve: 用于下一代命名实体识别和检索的数据集
Prompting ChatGPT in MNER: 提升辅助精炼知识的多模态命名实体识别
Taxonomy Expansion for Named Entity Recognition
MProto: 基于去噪最优运输的多原型网络远距离监督命名实体识别
Empirical Study of Zero-Shot NER with ChatGPT
Less than One-shot: 非常弱监督下的命名实体识别
A Boundary Offset Prediction Network for Named Entity Recognition
Enhancing Low-resource Fine-grained Named Entity Recognition by Leveraging Coarse-grained Datasets
EXPLAIN, EDIT, GENERATE: 基于反事实数据增强的多跳事实验证
In-context Learning for Few-shot Multimodal Named Entity Recognition
Addressing NER Annotation Noises with Uncertainty-Guided Tree-Structured CRFs
A Query-Parallel Machine Reading Comprehension Framework for Low-resource NER
Causal Intervention-based Few-Shot Named Entity Recognition
MultiCoNER v2: 多语言精细和嘈杂命名实体识别的大型数据集
NERvous About My Health: 构建印地语医疗命名实体识别数据集
Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition
GSAP-NER: 学术实体提取聚焦于机器学习模型和数据集的新型任务、语料库和基准
Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset
Re-weighting Tokens: 名称实体识别的码解防屏蔽源码简单有效主动学习策略
SmartSpanNER: 低资源场景下命名实体识别的稳健性
Toward a Critical Toponymy Framework for Named Entity Recognition: 纽约市案例研究
Biomedical Named Entity Recognition via Dictionary-based Synonym Generalization
SKD-NER: 通过强化学习的跨度知识蒸馏进行持续命名实体识别
CASSI: 基于上下文和语义结构的插值增强低资源命名实体识别
RE（关系抽取）Always the Best Fit: 从因果角度填充域差距的少样本关系抽取
Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation Extraction
Anaphor Assisted Document-Level Relation Extraction
Explore the Way: 通过连接实体构建推理路径进行跨文档关系抽取
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction
Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks
Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models
Chinese Metaphorical Relation Extraction
Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction
CoVariance-based Causal Debiasing for Entity and Relation Extraction
GPT-RE: 使用大型语言模型的上下文学习关系抽取
Reasoning Makes Good Annotators : 自动任务特定规则精炼框架低资源关系抽取
Towards Zero-shot Relation Extraction in Web Mining: 多模态方法结合相对XML路径的零样本关系抽取
A Spectral Viewpoint on Continual Relation Extraction
HFMRE: 使用哈夫曼树在袋中查找优秀实例进行远距离监督关系抽取
RAPL: 关系感知原型学习方法进行少样本文档级关系抽取
HyperNetwork-based Decoupling to Improve Model Generalization for Few-Shot Relation Extraction
Generating Commonsense Counterfactuals for Stable Relation Extraction
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs
Adaptive Hinge Balance Loss for Document-Level Relation Extraction
Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document
EE（事件检测和提取）Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction
AniEE: 动物实验文献的事件抽取数据集
An Iteratively Parallel Generation Method with the Pre-Filling Strategy for Document-level Event Extraction
Continual Event Extraction with Semantic Confusion Rectification
Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics
BioDEX: 生物医学药物不良事件提取的大型数据集
GLEN: 通用事件检测的数千种类型
GenKIE: 生成式多模态文档关键信息提取
Set Learning for Generative Information Extraction
Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction
Lazy-k Decoding: 信息抽取的约束解码
Mirror: 多种信息抽取任务的通用框架
Guideline Learning for In-Context Information Extraction
Open Information Extraction via Chunks
Reading Order Matters: 通过预测标记路径信息抽取富媒体文档
Information Extraction from Legal Wills: GPT-4的表现如何?
Efficient Data Learning for Open Information Extraction with Pre-trained Language Models
On Event Individuation for Document-Level Information Extraction
Abstractive Open Information Extraction
Preserving Knowledge Invariance: 信息抽取鲁棒性评估的重新思考
Dialogue Medical Information Extraction with Medical-Item Graph and Dialogue-Status Enriched Representation
From Speculation Detection to Trustworthy Relational Tuples in Information Extraction
Information Extraction（信息抽取）Instruct and Extract: 指令调整的按需信息抽取
RexUIE: 具有明确模式指导的通用信息抽取递归方法
GenKIE: 生成式多模态文档关键信息提取
Set Learning for Generative Information Extraction
Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction
Lazy-k Decoding: 信息抽取的约束解码
Mirror: 多种信息抽取任务的通用框架
Guideline Learning for In-Context Information Extraction
Open Information Extraction via Chunks
Reading Order Matters: 通过预测标记路径信息抽取富媒体文档
Information Extraction from Legal Wills: GPT-4的表现如何?
Efficient Data Learning for Open Information Extraction with Pre-trained Language Models
On Event Individuation for Document-Level Information Extraction
Abstractive Open Information Extraction
Preserving Knowledge Invariance: 信息抽取鲁棒性评估的重新思考
Dialogue Medical Information Extraction with Medical-Item Graph and Dialogue-Status Enriched Representation
From Speculation Detection to Trustworthy Relational Tuples in Information Extraction
MongoDB初学快速入门
MongoDB，作为非关系型数据库的码解一种，以其灵活的码解文档存储结构和强大的数据查询能力而闻名。安装MongoDB及MongoDB Database Tool，码解用户便能轻松地进行数据导入、码解导出，码解为项目开发提供便利。码解通过实例演示数据操作，码解手游平台程序源码用户能快速上手。码解
启动MongoDB，码解进行基础操作，如插入与查找数据。深入了解数据管理基础，为更复杂的派单接单php源码操作打下坚实基础。通过学习如何插入数据，用户能有效构建数据库，而查找功能则允许用户快速检索所需信息。
进阶查询操作涵盖了Limit和Count、Sort与Skip、$gt与$lt等。多商家商城源码这些操作帮助用户在大量数据中精确筛选所需信息，$gt与$lt尤其适用于特定范围内的数据筛选，而Limit和Count则允许用户控制结果数量，Sort与Skip则实现排序与跳过功能，使得数据呈现更加有序。
数组操作包括使用$or、驱动加速器源码$and、$all、$in等关键字，通过组合这些操作，用户能实现复杂的数据匹配，满足多样化的查询需求。
在修改数据方面，$set、$unset、inc等操作适用于字段值的修改，而当涉及数组字段时，$push、$pull等操作则更加适用，提供对数组元素的增删功能。此外，delete操作允许用户彻底移除数据库中的元素，实现高效的数据管理。
利用Pycharm与Mongo的连接，用户能进行更深层次的开发，如在ComplexEventExtraction事理图谱抽取实战中，实现数据的高效处理与分析。
总结，MongoDB以其强大的数据处理能力，成为了众多开发者的首选。通过本文提供的内容，希望读者能快速掌握MongoDB的基础及进阶操作，为项目开发提供有力支持。