Graph-to-text Generation
Graph-to-Text Generation is a natural language generation task that involves converting structured graph representations of data into coherent and contextually accurate natural language texts, distinguished by its focus on capturing relational and topological information encoded in graph structures.
198
Publications
10.7K
Citations
623
Authors
208
Institutions
Publications per year
2017–2026
151
Parents
198
Construction of the Literature Graph in Semantic Scholar
Waleed Ammar, Dirk Groeneveld, Chandra Bhagavatula et al. · 2018 · 325 citations · Full text
1–5 of 198
623
13
h-index
8
h-index
6
h-index
6
h-index
5
h-index
1–5 of 623
208

Peking University
Beijing, China
11 h-index
32 publications
1.2K citations
University of Illinois Urbana-Champaign
Urbana, United States
8 h-index
26 publications
2.1K citations
IBM (United States)
Armonk, United States
7 h-index
15 publications
1.2K citations
Rensselaer Polytechnic Institute
Troy, United States
6 h-index
9 publications
643 citations
Singapore University of Technology and Design
Singapore, Singapore
6 h-index
16 publications
1.3K citations

Renmin University of China
Beijing, China
5 h-index
14 publications
442 citations
Tencent (China)
Shenzhen, China
5 h-index
7 publications
438 citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
5 h-index
8 publications
646 citations
1–8 of 208
Repository · 31 publications · 1.2K citations
20
h-index
Conference · 4 publications · 592 citations
4
h-index
TACL · 3 publications · 240 citations
3
h-index
2 publications · 70 citations
2
h-index
JBCS · 2 publications · 240 citations
2
h-index
1–5