https://github.com/thunlp/explore-and-evaluate
공식 코드Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Data integration (also called information integration) is the process of consolidating data from a set of heterogeneous data sources into a single uniform data set (materialized integration) or view on the data (virtual integration). Data integration pipelines involve subtasks such as schema matching, table annotation, entity resolution, value normalization, data cleansing, and data fusion. Application domains of data integration include data warehousing, data lakes, and knowledge base consolidation. Surveys on Data integration:
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
Learning High-Quality and General-Purpose Phrase Representations
Combining Experimental and Historical Data for Policy Evaluation
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching
Generating Explanations to Understand and Repair Embedding-based Entity Alignment
BlueTempNet: A Temporal Multi-network Dataset of Social Interactions in Bluesky Social
Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective
MODIS: Multi-Omics Data Integration for Small and Unpaired Datasets
Wavelet Diffusion Models are fast and scalable Image Generators
Tracker Meets Night: A Transformer Enhancer for UAV Tracking
VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning
On Calibration of LLM-based Guard Models for Reliable Content Moderation
WearMask: Fast In-browser Face Mask Detection with Serverless Edge Computing for COVID-19
ISLAND: Interpolating Land Surface Temperature using land cover
SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.