Papers with Code 아카이브
Relation Extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 51
- 보존된 평가 기록
- 373
Relation Extraction is the task of predicting attributes and relations for entities in a sentence. For example, given a sentence “Barack Obama was born in Honolulu, Hawaii.”, a relation classifier aims at predicting the relation of “bornInCity”. Relation Extraction is the key component for building relation knowledge graphs, and it is of crucial significance to natural language processing applications such as structured search, sentiment analysis, question answering, and summarization.
Source: Deep Residual Learning for Weakly-Supervised Relation Extraction
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/akshayparakh25/relationhierarchy
공식 코드Taxonomical hierarchy of canonicalized relations from multiple Knowledge Bases
https://github.com/alibabaresearch/advancedliteratemachinery
공식 코드GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
https://github.com/alirezasalemi7/urag
공식 코드https://github.com/aliyun/cflue
공식 코드https://github.com/allanj/deductive-mwp
공식 코드Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
https://github.com/allenai/comb_dist_direct_relex
공식 코드Combining Distant and Direct Supervision for Neural Relation Extraction
https://github.com/allenai/drug-combo-extraction
공식 코드A Dataset for N-ary Relation Extraction of Drug Combinations
https://github.com/allenai/kb
공식 코드https://github.com/allenai/scibert
공식 코드https://github.com/alon-albalak/D-REX
공식 코드https://github.com/alsayyahi/timeline
공식 코드https://github.com/alteca/promptore
공식 코드PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction
https://github.com/amazon-research/tanl
공식 코드Structured Prediction as Translation between Augmented Natural Languages
https://github.com/amazon-science/e2e-docie
공식 코드REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking
https://github.com/amodaresi/CovEReD
공식 코드Consistent Document-Level Relation Extraction via Counterfactuals
https://github.com/andrewzhe/revisit-docred
공식 코드Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED
https://github.com/antct/cil
공식 코드CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
https://github.com/antct/multicast
공식 코드Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training
https://github.com/anushkasw/maxre
공식 코드https://github.com/aone-nlp/fsre-sacon
공식 코드Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction
https://github.com/aozmh/crake
공식 코드Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base
https://github.com/aritra23/dragonverseqa
공식 코드DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering
https://github.com/as18cia/thesis_work
공식 코드https://github.com/asadifar/HCqa
공식 코드HCqa: Hybrid and Complex Question Answering on Textual Corpus and Knowledge Graph
https://github.com/asahi417/relbert
공식 코드Distilling Relation Embeddings from Pre-trained Language Models
https://github.com/avramandrei/DeftEval
공식 코드UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction
https://github.com/aws-health-ai/multi_domain_lm
공식 코드An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training
https://github.com/ayyyq/dore
공식 코드DORE: Document Ordered Relation Extraction based on Generative Framework
https://github.com/banglab-udem-mila/nlp4matsci-acl23
공식 코드https://github.com/baodaiqin/UGDSRE
공식 코드Two Training Strategies for Improving Relation Extraction over Universal Graph
https://github.com/bekou/multihead_joint_entity_relation_extraction
공식 코드Joint entity recognition and relation extraction as a multi-head selection problem
https://github.com/bflashcp3f/PCNN-NMAR
공식 코드Structured Minimally Supervised Learning for Neural Relation Extraction
https://github.com/bflashcp3f/textlabs-xwlp-code
공식 코드Process-Level Representation of Scientific Protocols with Interactive Annotation
https://github.com/bids-xu-lab/biomedical-nlp-benchmarks
공식 코드https://github.com/bigai-nlco/docgnre
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.