paper-with-me

Papers

Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task

2020-07-01 · WS 2020 7 · Yuhui Sun, Mengxue Guo, Xiang Li, Jianwei Cui, Bin Wang

This paper describes the Xiaomi{'}s submissions to the IWSLT20 shared open domain translation task for Chinese{\textless}-{\textgreater}Japanese language pair. We explore different model ensembling strategies based on recent Transformer variants. We also further strengthen our systems via some effective techniques, such as data filtering, data selection, tagged back translation, domain adaptation, knowledge distillation, and re-ranking. Our resulting Chinese-{\textgreater}Japanese primary system ranked second in terms of character-level BLEU score among all submissions. Our resulting Japanese-{\textgreater}Chinese primary system also achieved a competitive performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationKnowledge DistillationRe-RankingTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN

2020-07-01 · WS 2020 7 · Ebrahim Ansari, Amittai Axelrod, Nguyen Bach, Ond{\v{r}}ej Bojar 외

The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offli…

Translation

The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022

2022-05-01 · IWSLT (ACL) 2022 5 · Bao Guo, Mengge Liu, Wen Zhang, Hexuan Chen 외

This system paper describes the Xiaomi Translation System for the IWSLT 2022 Simultaneous Speech Translation (noted as SST) shared task. We participate in the English-to-Mandarin Chinese Text-to-Text (noted as T2T) track…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationKnowledge Distillation+4

UFAL Submissions to the IWSLT 2016 MT Track

2016-12-01 · IWSLT 2016 12 · Ondřej Bojar, Ondřej Cífka, Jindřich Helcl, Tom Kocmi 외

We present our submissions to the IWSLT 2016 machine translation task, as our first attempt to translate subtitles and one of our early experiments with neural machine translation (NMT). We focus primarily on English→Cze…

Machine TranslationNMTTranslation

The IWSLT 2016 Evaluation Campaign

2016-12-01 · IWSLT 2016 12 · Mauro Cettolo, Jan Niehues, Sebastian Stüker, Luisa Bentivogli 외

The IWSLT 2016 Evaluation Campaign featured two tasks: the translation of talks and the translation of video conference conversations. While the first task extends previously offered tasks with talks from a different sou…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+2

The IWSLT 2019 Evaluation Campaign

2019-11-01 · EMNLP (IWSLT) 2019 11 · Jan Niehues, Rolando Cattoni, Sebastian Stüker, Matteo Negri 외

The IWSLT 2019 evaluation campaign featured three tasks: speech translation of (i) TED talks and (ii) How2 instructional videos from English into German and Portuguese, and (iii) text translation of TED talks from Englis…

Speech-to-TextTranslation