AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Attending to Entities for Better Text Understanding

Pengxiang Cheng, Katrin Erk

AAAI 2020 · Architectures and efficiency › Attention and transformers · approach: Long-context KV and memory attention · 41 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 CorefAll auxiliary supervision (ablation)BiDAF-SA-Early on LAMBADA · LAMBADA testaccuracy (%): 60.54 -> 61.51Improved
Add ELMo embeddings without CorefAll supervision (ablation)BiDAF-SA-Early on LAMBADA · LAMBADA testaccuracy (%): 60.54 -> 61.38Improved
Add CorefAll supervision to the ELMo-augmented model (ablation)BiDAF-SA-Early + ELMo on LAMBADA · LAMBADA testaccuracy (%): 61.38 -> 63.71Improved
Replace Stanford CoreNLP coreference signals with neural coreference signals (ablation)BiDAF-SA-Early + CorefAll on LAMBADA · LAMBADA testaccuracy (%): 61.51 -> 61.13Hurt
Add CorefAll supervision (ablation)BiDAF-SA-Early + ELMo on LAMBADA · LAMBADA dev, instances requiring coreferenceaccuracy: 48.5 ± 4.1 -> 62.0 ± 3.5Improved
Add CorefAll supervision (ablation)BiDAF-SA-Early + ELMo on LAMBADA · LAMBADA dev, pronoun targetsaccuracy: 72.31 ± 0.15 -> 76.72 ± 0.53Improved
Add CorefAll supervision (ablation)BiDAF-SA-Early on LAMBADA · LAMBADA testaccuracy (%): 59.48 -> 61.19Improved
Place the self-attention encoder early rather than late (ablation)BiDAF on LAMBADA · LAMBADA test, without auxiliary supervisionaccuracy (%): 59.48 -> 60.54Improved
Apply CorefAll supervision at the early rather than late encoder (ablation)BiDAF-SA-Both on LAMBADA · LAMBADA testaccuracy (%): 61.54 -> 61.72Improved
Use dependency-parse supervision instead of CorefAll (ablation)BiDAF-SA-Early on LAMBADA · LAMBADA testaccuracy (%): 61.51 -> 61.06Hurt
Use CorefPrev instead of CorefAll supervision (ablation)BiDAF-SA-Early on LAMBADA · LAMBADA testaccuracy (%): 61.51 -> 60.94Hurt
Use CorefNext instead of CorefAll supervision (ablation)BiDAF-SA-Early on LAMBADA · LAMBADA testaccuracy (%): 61.51 -> 61.27Hurt

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