AI Paper Atlas

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

Neural Character-level Dependency Parsing for Chinese

Haonan Li, Zhisong Zhang, Yuqi Ju, Hai Zhao

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 32 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 ROOT-CHAR+WORD character POS tags vs none (ablation)Char LSTM Parser · CTB5 character-level, devUAS: 68.92 -> 89.51Improved
use ROOT-CHAR+WORD instead of CHAR+WORD tags (ablation)Char LSTM Parser · CTB5 character-level, devLAS: 80.31 -> 87.45Improved
use ROOT-CHAR+WORD instead of CHAR+WORD tags (ablation)Char LSTM Parser · CTB5 character-level, devUAS: 87.24 -> 89.51Improved
use word-level tags only instead of character-level tags only (ablation)Char LSTM Parser · CTB5 character-level, devUAS: 71.87 -> 79.49Improved
add character position info to word tags (WORD+CHAR-POSIT vs WORD-ONLY) (ablation)Char LSTM Parser · CTB5 character-level, devUAS: 79.49 -> 88.61Improved
use ROOT-CHAR+WORD instead of WORD+CHAR-POSIT (ablation)Char LSTM Parser · CTB5 character-level, devLAS: 80.67 -> 87.45Improved
use LSTM parser instead of MaltParser at character levelChar parser · CTB5 character-level, testUAS: 83.72 -> 90.00Improved
use gold instead of predicted character POSChar LSTM Parser · CTB5 character-level, testUAS: 82.53 -> 90.00Improved
character-level LSTM parser instead of word-level LSTM pipelineparser · CTB5 pipeline CMCM: 26.86 -> 34.36Improved
character-level parser with predicted POS vs word-level restoration comparison with Zhang 2014Our model · CTB5 word-level dependencyUAS: 82.14 -> 79.44Hurt

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