AI Paper Atlas

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

Multi-Point Semantic Representation for Intent Classification

Jinghan Zhang, Yuxiao Ye, Yue Zhang, Likun Qiu, Bin Fu, Yang Li, Zhenglu Yang, Jian Sun

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 6 citations (OpenAlex)

Read the paper

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 query-label attention (ablation)CIBA(word only) · TELE testACC: 0.9044 -> 0.9089Improved
add label-factor aligned attention (ablation)CIBA(word only) · TELE testACC: 0.9060 -> 0.9089Improved
add coarse-grained label information to factor-only model (ablation)CIBA(word only) · TELE testACC: 0.8983 -> 0.9089Improved
add factor information to label-only model (ablation)CIBA(word only) · TELE testACC: 0.8977 -> 0.9089Improved
use all four factors instead of topic only (ablation)CIBA(word only) · TELE testACC: 0.8883 -> 0.9089Improved
use all four factors instead of predicate only (ablation)CIBA(word only) · TELE testACC: 0.8917 -> 0.9089Improved
use all four factors instead of object/condition only (ablation)CIBA(word only) · TELE testACC: 0.8962 -> 0.9089Improved
use all four factors instead of query type only (ablation)CIBA(word only) · TELE testACC: 0.8867 -> 0.9089Improved
add BERT embeddings to CIBACIBA(word only) · CCL testACC: 0.9436 -> 0.9472Improved
add BERT embeddings to CIBACIBA(word only) · TELE testACC: 0.9089 -> 0.9226Improved
add BERT embeddings to CIBACIBA(word only) · ECOM testACC: 0.8546 -> 0.8622Improved
add BERT embeddings to CIBACIBA(word only) · CitySrv testACC: 0.8373 -> 0.8320Hurt

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