AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Dependency Grammar Induction with a Neural Variational Transition-Based Parser

Bowen Li, Jianpeng Cheng, Yang Liu, Frank Keller

AAAI 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Amortized and online variational inference

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 universal-rule posterior regularization (ablation)Neural variational transition parser · WSJ-10DDA: 33.3 (39.0) -> 54.7 (58.2)Improved
add pretraining with direct posterior-regularization reward (ablation)Posterior-regularized model · WSJ-10DDA: 47.5 (59.8) -> 64.8 (67.1)Improved
add pretraining with direct posterior-regularization reward (ablation)Posterior-regularized model · WSJDDA: 36.7 (46.3) -> 42.0 (43.7)Improved
replace conventional learned baseline with within-sample score normalization (ablation)Posterior-regularized model with pretraining · WSJ-10DDA: 58.7 -> 60.8Improved
add polarity correction using the number of universal rules (ablation)RL-SN · WSJ-10DDA: 60.8 -> 66.7Improved
replace polarity-corrected normalized score with normalized rule-count score (ablation)Posterior-regularized model with pretraining · WSJ-10DDA: 66.7 -> 64.4Hurt
initialize rule expectations from annotated training rules instead of uniformly (ablation)Posterior-regularized parser · WSJ-10DDA: 54.7 -> 66.7Improved
add lexicalized word-token features (ablation)WeaklySupervised parser · WSJ-10DDA: 66.7 (67.6) -> 68.2 (71.1)Improved
use the proposed transition-based parser instead of RF+H1+H2Dependency grammar induction · WSJ-10DDA: 51.0 (52.7) -> 54.7 (58.2)Improved
use the proposed transition-based parser instead of RF+H1+H2Dependency grammar induction · UD average, length ≤ 40DDA: 31.9 (36.2) -> 50.8 (52.5)Improved
use the proposed unlexicalized parser instead of LC-DMVDependency grammar induction · French UD, all lengthstokens per second: 74 -> 1191Improved

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