atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

A Representation Learning Framework for Multi-Source Transfer Parsing

AAAI 2016 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 104 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
add unified multilingual lexical features (MULTI-PROJ) (ablation)MULTI-DELEX · Google UDT v2.0 AVGLAS: 62.79 -> 69.32Helped
add unified multilingual lexical features (MULTI-SG) (ablation)MULTI-DELEX · Google UDT v2.0 AVGLAS: 62.79 -> 67.97Helped
use multilingual robust projection instead of multilingual skip-gram (ablation)MULTI-SG · Google UDT v2.0 AVGLAS: 67.97 -> 69.32Helped
use multi-source treebanks instead of English-only source (delexicalized)Guo15 · Google UDT v2.0 ESLAS: 62.28 -> 64.68Helped
use multi-source treebanks instead of English-only source (delexicalized)Guo15 · Google UDT v2.0 DELAS: 51.54 -> 49.82Hurt
fine-tune on 50 target-language sentencesMULTI-PROJ · Google UDT v2.0 AVGLAS: +4.41Helped
fine-tune on 50 target-language sentencesMULTI-DELEX · Google UDT v2.0 ESUAS: 73.46(−2.08)Hurt

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