SOTAVerified

KG-to-Text Generation

Knowledge-graph-to-text (KG-to-text) generation aims to generate high-quality texts which are consistent with input graphs.

Description from: JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs

Papers

Showing 110 of 22 papers

TitleStatusHype
MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation0
FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode0
Can Knowledge Graphs Simplify Text?Code1
Generating Faithful Text From a Knowledge Graph with Noisy Reference Text0
Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge GraphsCode0
Knowledge Graph for NLG in the context of conversational agents0
Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic ConsistencyCode0
GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationCode1
EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text GenerationCode0
WikiGraphs: A Wikipedia Text - Knowledge Graph Paired DatasetCode0
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GAP - Me,reROUGE76.22Unverified
2GAP - Me,r+γBLEU66.2Unverified
3JointGT (T5)BLEU66.14Unverified
4JointGT (BART)BLEU65.92Unverified
5JointGT (BART) - w/ JointGTPretrainBLEU65.92Unverified
6JointGT (BART) - w/ BARTPretrainBLEU64.6Unverified
7BARTBLEU64.55Unverified
8T5BLEU64.42Unverified
9KGPTBLEU64.11Unverified
10KGPT w/o pretrainBLEU62.3Unverified