HyperAI超神経
ホーム
ニュース
最新論文
チュートリアル
データセット
百科事典
SOTA
LLMモデル
GPU ランキング
学会
検索
サイトについて
日本語
HyperAI超神経
Toggle sidebar
サイトを検索…
⌘
K
ホーム
SOTA
Relation Extraction
Relation Extraction On Ace 2005
Relation Extraction On Ace 2005
評価指標
Cross Sentence
Relation classification F1
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
Columns
モデル名
Cross Sentence
Relation classification F1
Paper Title
Repository
Dual Pointer Network(multi-head)
No
80.8
Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence
-
Multi-turn QA
No
-
Entity-Relation Extraction as Multi-Turn Question Answering
RNN+CNN
No
67.7
Combining Neural Networks and Log-linear Models to Improve Relation Extraction
-
SPTree
No
-
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
TablERT
No
-
Named Entity Recognition and Relation Extraction using Enhanced Table Filling by Contextualized Representations
MRC4ERE++
No
-
Asking Effective and Diverse Questions: A Machine Reading Comprehension based Framework for Joint Entity-Relation Extraction
MGE
No
-
A Multi-Gate Encoder for Joint Entity and Relation Extraction
-
HySPA
No
-
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction
ASP+T5-3B
Yes
-
Autoregressive Structured Prediction with Language Models
Walk-based model
No
64.2
A Walk-based Model on Entity Graphs for Relation Extraction
DYGIE++
Yes
-
Entity, Relation, and Event Extraction with Contextualized Span Representations
Table-Sequence
No
-
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
PL-Marker
Yes
-
Packed Levitated Marker for Entity and Relation Extraction
CNN
No
61.3
-
-
Dual Pointer Network
No
80.5
Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism
-
GoLLIE
-
-
GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
MRT
No
-
Extracting Entities and Relations with Joint Minimum Risk Training
-
Joint w/ Global
No
-
-
-
Span-level
No
-
Span-Level Model for Relation Extraction
-
Hierarchical Multi-task
No
-
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
0 of 30 row(s) selected.
Previous
Next