paper-with-me

Papers

AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task

2022-05-12 · Patrick Wilken, Evgeny Matusov

To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for English-to-German with various mechanisms of length control, ranging from source-side and target-side pseudo-tokens to encoding of remaining length in characters that replaces positional encoding. We further increased translation length compliance by sentence-level selection of length-compliant hypotheses from different system variants, as well as rescoring of N-best candidates from a single system. Length-compliant back-translated and forward-translated synthetic data, as well as other parallel data variants derived from the original MuST-C training corpus were important for a good quality/desired length trade-off. Our experimental results show that length compliance levels above 90% can be reached while minimizing losses in MT quality as measured in BERT and BLEU scores.

📄 PDF Abstract BibTeX arXiv:2205.05807

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Weight Decay 설명 없음
WordPiece 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

AppTek’s Submission to the IWSLT 2022 Isometric Spoken Language Translation Task

2022-05-01 · IWSLT (ACL) 2022 5 · Patrick Wilken, Evgeny Matusov

To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for English-to-German with various mechanisms of len…

SentenceTranslation

HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation

2022-05-01 · IWSLT (ACL) 2022 5 · Zongyao Li, Jiaxin Guo, Daimeng Wei, Hengchao Shang 외

This paper presents our submissions to the IWSLT 2022 Isometric Spoken Language Translation task. We participate in all three language pairs (English-German, English-French, English-Spanish) under the constrained setting…

DecoderTranslation

Hierarchical Multi-task learning framework for Isometric-Speech Language Translation

2022-05-01 · IWSLT (ACL) 2022 5 · Aakash Bhatnagar, Nidhir Bhavsar, Muskaan Singh, Petr Motlicek

This paper presents our submission for the shared task on isometric neural machine translation in International Conference on Spoken Language Translation (IWSLT). There are numerous state-of-art models for translation pr…

Machine TranslationMulti-Task LearningTranslation

Findings of the IWSLT 2022 Evaluation Campaign

2022-05-01 · IWSLT (ACL) 2022 5 · Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito 외

The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech transl…

Speech-to-Speech TranslationTranslation

Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021

2021-08-01 · ACL (IWSLT) 2021 8 · Parnia Bahar, Patrick Wilken, Mattia A. Di Gangi, Evgeny Matusov

This paper describes the offline and simultaneous speech translation systems developed at AppTek for IWSLT 2021. Our offline ST submission includes the direct end-to-end system and the so-called posterior tight integrate…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationMachine Translation+3