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.

AppTek 使用基于神经 Transformer 的系统对英语到德语的音–语翻译任务进行了改进，通过使用源端伪标记、目标端伪标记和使用剩余字符长度编码来实现长度控制，同时使用由 MuST-C 原始语料库派生的合成数据，使翻译满足长度条件，研究结果表明，可以在最小化 BERT 和 BLEU 分数损失的同时实现超过 90％的长度符合度。

AppTek 提交给 IWSLT 2022 同构口语语言翻译任务

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

In this paper, we introduce a hybrid search for attention-based neural
machine translation (NMT). A target phrase learned with statistical MT models
extends a hypothesis in the NMT beam search when the attention of the NMT model
focuses on the source words translated by this phrase. Phrases added in this
way are scored with the NMT model, but also with SMT features including
phrase-level translation probabilities and a target language model.
Experimental results on German->English news domain and English->Russian
e-commerce domain translation tasks show that using phrase-based models in NMT
search improves MT quality by up to 2.3% BLEU absolute as compared to a strong
NMT baseline.

本文介绍了一种混合搜索的关注机制神经机器翻译模型，该模型使用机器翻译模型和短语级翻译概率等特征来实现目标短语的波束搜索，结果显示与强 NMT 基准模型相比，使用短语模型搜索可以将机器翻译质量提高达到 2.3% 的 BLEU 绝对值的效果。