atlas

Research map / Architectures and efficiency / RNNs and normalization

Discontinuous Constituent Parsing with Pointer Networks

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: Non-autoregressive translation · 21 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
Use the joint Pointer Network and biaffine labelerDiscontinuous constituent parsing · NEGRA, predicted POS tagsF1: 83.2 -> 85.4Helped
Use the joint Pointer Network and biaffine labelerDiscontinuous constituent parsing · TIGER, predicted POS tagsF1: 82.7 -> 85.3Helped
Add gold POS tags instead of using predicted POS tagsThis work · NEGRAF1: 85.4 -> 86.1Helped
Add gold POS tags instead of using predicted POS tagsThis work · TIGERF1: 85.3 -> 86.3Helped
Remove POS tag embeddings (ablation)This work · NEGRAF1: 85.4 -> 85.7No clear effect
Remove POS tag embeddings (ablation)This work · TIGERF1: 85.3 -> 85.7No clear effect
Remove POS tag embeddings and pretrained word embeddings (ablation)This work · NEGRAF1: 85.4 -> 83.7Hurt
Remove POS tag embeddings and pretrained word embeddings (ablation)This work · TIGERF1: 85.3 -> 84.6Hurt

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