AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

What Happens Next? Event Prediction Using a Compositional Neural Network Model

AAAI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 157 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
learn nonlinear neural composition of predicate and arguments plus coherence function (ablation)WORD2VEC-PRED+ARG · MCNC (Gigaword NYT test)accuracy: 42.23 -> 49.57Helped
add argument headword embeddings (ablation)WORD2VEC-PRED · MCNC (Gigaword NYT test)accuracy: 40.17 -> 42.23Helped
add argument embeddings by vector addition (ablation)MIKOLOV-VERB · MCNC (Gigaword NYT test)accuracy: 24.57 -> 28.97Helped
learn predicate-GR embeddings from event chains with word2vec instead of PPMIC&J08 · MCNC (Gigaword NYT test)accuracy: 30.52 -> 40.17Helped
bigram conditional probability instead of PPMIC&J08 · MCNC (Gigaword NYT test)accuracy: 30.52 -> 29.67No clear effect
LSI distributional vectors instead of PPMIC&J08 · MCNC (Gigaword NYT test)accuracy: 30.52 -> 27.94Hurt
autoencoder pretraining of event composition layers (ablation)EVENT-COMP · MCNC (Gigaword NYT test)accuracyNo clear effect

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