Researchers from ByteDance AILab and Shanghai Jiao Tong University have introduced Xiaomingbot, a multilingual and multimodal news reporter. The paper Xiaomingbot: A Multilingual Robot News Reporter is available on arXiv.

ByteDance AILab和上海交通大学的研究人员介绍了多语言和多模式新闻记者Xiaomingbot。 论文《 小明机器人：多语言机器人新闻记者》可在arXiv上找到 。

The solutions is interesting as it tries to consider how automation can be done in certain tasks in sports and financial reporting.

该解决方案很有趣，因为它试图考虑如何在体育和财务报告中的某些任务中实现自动化。

It contains four components:

它包含四个组成部分：

1. News generator.
   新闻发生器。
2. News translator.
   新闻翻译。
3. A cross-lingual newsreader.
   跨语言新闻阅读器。
4. Animated avatar.
   动画头像。

You can see all of these in the video below.

您可以在下面的视频中看到所有这些内容。

It can work from summarising text and then taking the necessary action to represent these through the four aforementioned components.

它可以从总结文本开始，然后采取必要的行动来通过上述四个组成部分来表示这些内容。

The paper summarises it in the following way [with added numeration]:

本文通过以下方式进行了总结[增加了编号]：

1. “First, it learns how to write news articles based on a text generation model, and summarize the news through an extraction based method.

   “首先，它学习如何基于文本生成模型撰写新闻文章，并通过基于提取的方法总结新闻。

2. Next, its system translates the summarization into multiple languages. Finally, the system produces the video of an animated avatar reading the news with synthesized voice. Owing to the voice cloning model that can learn from a few Chinese audio samples, Xiaomingbot can maintain consistency in intonation and voice projection across different languages.”

   接下来，其系统将摘要翻译成多种语言。 最终，系统生成动画化身的视频，并以合成语音读取新闻。 由于可以从一些中文音频样本中学习的语音克隆模型，小明博能够在不同语言中保持语调和语音投影的一致性。”

This is an interesting step to take insights from natural language generation as well as natural language processing to commercial application.

这是从自然语言生成以及自然语言处理到商业应用的深刻见解的有趣一步。

This is #500daysofAI and you are reading article 415. I am writing one new article about or related to artificial intelligence every day for 500 days.

这是＃500daysofAI，您正在阅读第415条。我连续500天每天都在撰写一篇有关人工智能或与人工智能有关的新文章。