https://github.com/pku-tangent/docred-fe
공식 코드DocRED-FE: A Document-Level Fine-Grained Entity And Relation Extraction Dataset
Papers with Code 아카이브
Relation Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 8
- 보존된 평가 기록
- 33
Relation Classification is the task of identifying the semantic relation holding between two nominal entities in text.
Source: Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/pnborchert/core
공식 코드CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation
https://github.com/pnborchert/multirep
공식 코드https://github.com/qingwang-isu/mixore
공식 코드Towards a More Generalized Approach in Open Relation Extraction
https://github.com/qipeng/gcn-over-pruned-trees
공식 코드Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
https://github.com/rajatkoner08/rtn
공식 코드https://github.com/ritvikshrivastava/multitask_transformers
공식 코드"Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space
https://github.com/s-nlp/konstruktor
공식 코드Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering
https://github.com/sa5r/mrca
공식 코드Multiple Relations Classification using Imbalanced Predictions Adaptation
https://github.com/saintfe/rdr
공식 코드Do Models Learn the Directionality of Relations? A New Evaluation: Relation Direction Recognition
https://github.com/snowood1/zero-shot-plover
공식 코드Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
https://github.com/studio-ousia/luke
공식 코드LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
https://github.com/suamin/umls-medline-distant-re
공식 코드A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction
https://github.com/synapse-developpement/Discovery
공식 코드Mining Discourse Markers for Unsupervised Sentence Representation Learning
https://github.com/takase/relPatSim
공식 코드Composing Distributed Representations of Relational Patterns
https://github.com/thunlp/ERNIE
공식 코드ERNIE: Enhanced Language Representation with Informative Entities
https://github.com/thunlp/PTR
공식 코드https://github.com/thunlp/fewrel
공식 코드FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
https://github.com/tianran/vecdcs
공식 코드Learning Semantically and Additively Compositional Distributional Representations
https://github.com/tuur/WLLETlinkClassification
공식 코드Word-Level Loss Extensions for Neural Temporal Relation Classification
https://github.com/vasevarad/Discourse-Relation-Embeddings
공식 코드Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media
https://github.com/vered1986/LexNET
공식 코드https://github.com/vt-nlp/syntax-guided-graph-transformer
공식 코드Extracting Temporal Event Relation with Syntax-guided Graph Transformer
https://github.com/weiminxiong/rationalecl
공식 코드Rationale-Enhanced Language Models are Better Continual Relation Learners
https://github.com/wentaoyuan/sornet
공식 코드SORNet: Spatial Object-Centric Representations for Sequential Manipulation
https://github.com/wisper12933/LMRC
공식 코드LLM with Relation Classifier for Document-Level Relation Extraction
https://github.com/wjn1996/PCNN_RL_HME
공식 코드https://github.com/wjw136/clean_lave
공식 코드On the use of Silver Standard Data for Zero-shot Classification Tasks in Information Extraction
https://github.com/xianjun-yang/pcmsp
공식 코드https://github.com/xwjim/DocRE-Rec
공식 코드https://github.com/ycm094/mg-fte-main
공식 코드Mutually Guided Few-shot Learning for Relational Triple Extraction
https://github.com/zjunlp/deepke
공식 코드https://github.com/2023-MindSpore-1/ms-code-156
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
https://github.com/Beacontownfc/paddle_luke_stable
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
https://github.com/DavidMortensen/Bachelor-readinglist
https://github.com/JiachengLi1995/UCTopic
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.