Formality plays a significant role in language communication, especially in
low-resource languages such as Hindi, Japanese and Korean. These languages
utilise formal and informal expressions to convey messages based on social
contexts and relationships. When a language translation technique is used to
translate from a source language that does not pertain the formality (e.g.
English) to a target language that does, there is a missing information on
formality that could be a challenge in producing an accurate outcome. This
research explores how this issue should be resolved when machine learning
methods are used to translate from English to languages with formality, using
Hindi as the example data. This was done by training a bilingual model in a
formality-controlled setting and comparing its performance with a pre-trained
multilingual model in a similar setting. Since there are not a lot of training
data with ground truth, automated annotation techniques were employed to
increase the data size. The primary modeling approach involved leveraging
transformer models, which have demonstrated effectiveness in various natural
language processing tasks. We evaluate the official formality accuracy(ACC) by
comparing the predicted masked tokens with the ground truth. This metric
provides a quantitative measure of how well the translations align with the
desired outputs. Our study showcases a versatile translation strategy that
considers the nuances of formality in the target language, catering to diverse
language communication needs and scenarios.

研究探索了在使用机器学习方法将英语翻译成带有形式化特征语言时，如何解决形式化信息缺失的问题，通过使用印地语作为示例数据，在形式化受控环境中训练双语模型，并与预训练的多语言模型在类似环境中的性能进行比较。主要建模方法是利用转换器模型，通过比较预测的被标记词与期望输出的实际词的准确度（ACC）来评估正式性准确性。这项研究展示了一种灵活的翻译策略，考虑了目标语言中形式化的细微差别，迎合了多样化的语言交流需求和场景。

用机器翻译控制目标语言的正式特征

Machine Translation to Control Formality Features in the Target Language

One of the things that need to change when it comes to machine translation is
the models' ability to translate code-switching content, especially with the
rise of social media and user-generated content. In this paper, we are
proposing a way of training a single machine translation model that is able to
translate monolingual sentences from one language to another, along with
translating code-switched sentences to either language. This model can be
considered a bilingual model in the human sense. For better use of parallel
data, we generated synthetic code-switched (CSW) data along with an alignment
loss on the encoder to align representations across languages. Using the WMT14
English-French (En-Fr) dataset, the trained model strongly outperforms
bidirectional baselines on code-switched translation while maintaining quality
for non-code-switched (monolingual) data.

我们提出了一种训练单一机器翻译模型的方法，该模型能够将单语句从一种语言翻译成另一种语言，并能够翻译混合语句到任意一种语言，以应对社交媒体和用户生成内容的崛起带来的语种切换翻译需求。该模型可被视为与人类类似的双语模型，并通过生成合成的混合语数据以及对编码器进行对齐损失来更好地使用并行数据。在使用 WMT14 英法数据集进行训练后，所训练的模型在混合语翻译中大幅优于双向基线模型，并且在非混合语（单语）数据上保持了质量。

对齐目标对语码转换翻译的影响

The Effect of Alignment Objectives on Code-Switching Translation

Large language models (LLMs) have shown impressive ability for open-domain
NLP tasks. However, LLMs are sometimes too footloose for natural language
understanding (NLU) tasks which always have restricted output and input format.
Their performances on NLU tasks are highly related to prompts or demonstrations
and are shown to be poor at performing several representative NLU tasks, such
as event extraction and entity typing. To this end, we present SeqGPT, a
bilingual (i.e., English and Chinese) open-source autoregressive model
specially enhanced for open-domain natural language understanding. We express
all NLU tasks with two atomic tasks, which define fixed instructions to
restrict the input and output format but still ``open'' for arbitrarily varied
label sets. The model is first instruction-tuned with extremely fine-grained
labeled data synthesized by ChatGPT and then further fine-tuned by 233
different atomic tasks from 152 datasets across various domains. The
experimental results show that SeqGPT has decent classification and extraction
ability, and is capable of performing language understanding tasks on unseen
domains. We also conduct empirical studies on the scaling of data and model
size as well as on the transfer across tasks. Our model is accessible at
this https URL

SeqGPT 是一种增强的双语模型，专门用于开放领域自然语言理解，通过两个原子任务来表达所有的 NLU 任务并进行指令微调和深度微调，展示了良好的分类和抽取能力，可在未见领域上执行语言理解任务。