AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation

Chengyi Wang, Yu Wu, Shujie Liu, Zhenglu Yang, Ming Zhou

AAAI 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 81 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
Use TCEN instead of pretrain+MTLLSTM speech translation · ST-TED En-De (subword average)BLEU: +3.6 BLEUImproved
Use TCEN instead of pretrain+MTLLSTM speech translation with character decoding · ST-TED En-De (character average)BLEU: +2.2 BLEUImproved
Use TCEN instead of pretrain+MTLTransformer speech translation · ST-TED En-De tst2013BLEU: 17.11 vs 14.98; 2.1 BLEUImproved
Use TCEN instead of the cascaded ASR-MT systemspeech translation · ST-TED En-DeBLEU: our model outperforms the simple cascaded model over 2 BLEU scoresImproved
Use TCEN instead of cascaded+re-segspeech translation · ST-TED En-De tst2010, tst2013, tst2014, tst2015BLEU: 17.61 vs 17.12; 17.67 vs 17.77; 15.73 vs 14.94; 14.94 vs 15.01Mixed
Use TCEN instead of the strongest listed prior E2E resultLSTM speech translation · Librispeech En-Fr testBLEU: 17.05 vs 17.02No clear effect
Add noisy CTC-path MT inputs (ablation)TCEN · ST-TED En-De tst2013BLEU: 14.95 -> 15.50Improved
Share CTC classification and source embedding weights (ablation)TCEN · ST-TED En-De tst2013BLEU: 14.02 -> 15.50Improved
Pre-train the model before fine-tuning (ablation)TCEN · ST-TED En-De tst2013BLEU: 8.42 -> 15.50Improved

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