atlas

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

Never Retreat, Never Retract: Argumentation Analysis for Political Speeches

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 44 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 two cascaded binary classifiers instead of one 3-class classifier (ablation)SVM relation classifier · Nixon-Kennedy 1960precision: 0.57 vs 0.72 (end-to-end accuracy)Helped
evaluate on Step 1 output instead of gold related pairsStep 2 classifier · Nixon-Kennedy 1960accuracy: 0.82 -> 0.72Hurt
minimum wage topic versus other topicsStep 2 classifier · Nixon-Kennedy 1960 minimum wageaccuracy: 0.94Helped
pairs by same speaker versus different speakersStep 2 classifier · Nixon-Kennedy 1960accuracy: 0.86 vs 0.79Helped
SVM pipeline versus random baseline on gold pairsrandom baseline · Nixon-Kennedy 1960 Step 2 goldaccuracy: 0.70 -> 0.82Helped
SVM pipeline versus random baseline on end-to-endrandom baseline · Nixon-Kennedy 1960 Step 2 end-to-endaccuracy: 0.51 -> 0.72Helped

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