AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation

David Alfonso-Hermelo, Ahmad Rashid, Abbas Ghaddar, Philippe Langlais, Mehdi Rezagholizadeh

NeurIPS 2021 · Large language models › Language, safety and interpretability · approach: Speech and audio language models · 0 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
Apply one random NATURE operator per utteranceStack-Prop+BERT evaluation · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 80.6 -> 59.0Hurt
Select the lowest-confidence NATURE operator per utteranceStack-Prop+BERT evaluation · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 80.6 -> 28.9Hurt
Apply one random NATURE operator per utteranceBi-RNN evaluation · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 74.3 -> 50.3Hurt
Select the lowest-confidence NATURE operator per utteranceBi-RNN evaluation · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 74.3 -> 23.0Hurt
Add an end-of-sentence filler (ablation)Stack-Prop+BERT · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 80.6 -> 40.3Hurt
Replace an adjective with a BERT candidate (ablation)Stack-Prop+BERT · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 80.6 -> 44.7Hurt
Replace an adverb with a BERT candidate (ablation)Stack-Prop+BERT · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 80.6 -> 43.7Hurt
Augment training and validation data using NLPaug strategiesStack-Prop+BERT · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy on Hard: 28.9 -> 40.6 (+11.7)Improved
Augment training and validation data using NLPaug strategiesStack-Prop+BERT · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy on Orig: 80.6 -> 78.3 (-2.3)Hurt
Apply Checklist punctuation perturbationsStack-Prop+BERT · ATIS, SNIPS, NLU-ED (Avg.)E2E accuracy: 80.6 -> 26.6Hurt

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