AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

SemSUM: Semantic Dependency Guided Neural Abstractive Summarization

Hanqi Jin, Tianming Wang, Xiaojun Wan

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 60 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic dependency graph encoderTransformer · Gigaword testROUGE-2 F1: 18.08 -> 19.75Improved
add semantic dependency graph encoderTransformer · Gigaword testBERTScore F1: 60.48 -> 61.56Improved
add semantic dependency graph encoderTransformer · DUC2004 testROUGE-1 recall: 29.78 -> 31.00Improved
add semantic dependency graph encoderTransformer · MSR-ATC testROUGE-2 F1: 12.45 -> 17.08Improved
graph attention encoder instead of GCNTFM&GCN · Gigaword testROUGE-2 F1: 19.03 -> 19.75Improved
add graph encoder to sentence encoder (ablation)SemSUM · Gigaword devROUGE-2 F1: 24.94 -> 26.54Improved
add sentence encoder to graph encoder (ablation)SemSUM · Gigaword devROUGE-2 F1: 25.21 -> 26.54Improved
add layer aggregation (BiLSTM) (ablation)SemSUM · Gigaword devROUGE-2 F1: 25.83 -> 26.54Improved
separate in/out direction mappings (ablation)SemSUM · Gigaword devROUGE-2 F1: 25.57 -> 26.54Improved
add position-adjacent relations as edge type to graph-only encoder (ablation)SemSUM graph-only · Gigaword devROUGE-2 F1: 25.21 -> 25.51Improved
SemSUM vs BiSETSemSUM · Gigaword testROUGE-2 F1: 19.78 vs 19.75Mixed
add semantic graphTransformer · Gigaword human evalinformativeness: 3.27 -> 3.8Improved

Later papers that compared with this method

1 later accepted paper reports SemSUM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy