AI Paper Atlas

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

Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization

Wataru Hirota, Yoshihiko Suhara, Behzad Golshan, Wang-Chiew Tan

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 6 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
Fine-tune LASER with semantic classification using L2-constrained softmax and center loss, plus language-adversarial trainingLASER · Cross-lingual intent classification, TrustYou, ATIS, and QuoraAcc@1Improved
Add a language discriminator to Emu (ablation)Emu · TrustYouAcc@1: 1.45 percentage pointsImproved
Add a language discriminator to Emu (ablation)Emu · ATISAcc@1: 2.81 percentage pointsImproved
Add a language discriminator to Emu (ablation)Emu · QuoraAcc@1: 1.05 percentage pointsImproved
Add center loss (ablation)Emu without center loss · TrustYouAcc@1: -0.44 percentage pointsHurt
Add center loss (ablation)Emu without center loss · ATISAcc@1: 0.04 percentage pointsNo clear effect
Add center loss (ablation)Emu without center loss · QuoraAcc@1: 6.00 percentage pointsImproved
Replace randomly sampled non-parallel adversarial sentences with parallel sentences (ablation)Emu · TrustYou, ATIS, and QuoraAcc@1: -0.5 points, -1.2 points, and -5.9 pointsHurt
Fine-tune with common contrastive, N-pair, or softmax losses instead of the proposed lossesLASER · Cross-lingual intent classification across the three datasetsAcc@1Hurt
Use the semantic classifier directly for intent detection instead of nearest-neighbor similarityEmu · Cross-lingual intent classificationclassification performanceHurt

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