AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Generating Live Soccer-Match Commentary from Play Data

Yasufumi Taniguchi, Yukun Feng, Hiroya Takamura, Manabu Okumura

AAAI 2019 · Architectures and efficiency › Attention and transformers · approach: Long-context KV and memory attention

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 placeholders for player/team names (Model 2 vs 1) (ablation)encoder-decoder baseline · Soccer live commentary test setBLEU: 0.11 -> 0.43Improved
add placeholders for player/team names (Model 2 vs 1) (ablation)encoder-decoder baseline · Soccer live commentary test set (human eval)informativeness: 1.41 -> 1.38No clear effect
add gate mechanism to placeholder model (Model 3 vs 2) (ablation)Model 2 · Soccer live commentary test setBLEU: 0.43 -> 0.58Improved
add gate mechanism to placeholder+reconstruction model (Model 5 vs 4) (ablation)Model 4 · Soccer live commentary test setBLEU (l<=10): 6.38 -> 7.46Improved
add gate mechanism to placeholder+reconstruction model (Model 5 vs 4) (ablation)Model 4 · Soccer live commentary test setBLEU: 0.65 -> 0.51Hurt
add reconstruction error to placeholder model (Model 4 vs 2) (ablation)Model 2 · Soccer live commentary test setBLEU: 0.43 -> 0.65Improved
add reconstruction error to gate+placeholder model (Model 5 vs 3) (ablation)Model 3 · Soccer live commentary test setBLEU (l<=10): 5.19 -> 7.46Improved
add reconstruction error to gate+placeholder+word concat (Model 7 vs 6) (ablation)Model 6 · Soccer live commentary test setBLEU: 0.12 -> 0.69Improved
add word concatenation of frequent bigrams (Model 7 vs 5) (ablation)Model 5 · Soccer live commentary test setBLEU: 0.51 -> 0.69Improved
add word concatenation of frequent bigrams (Model 7 vs 5) (ablation)Model 5 · Soccer live commentary test setBLEU (l<=10): 7.46 -> 6.79Hurt
add reconstruction error (Model 5 vs 3) (ablation)Model 3 · Soccer live commentary test set (human eval)grammaticality: 1.89 -> 1.99Improved
full model vs baseline (Model 7 vs 1) (ablation)baseline · Soccer live commentary test set (human eval)informativeness: 1.41 -> 1.69Improved

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