We present TwHIN-BERT, a multilingual language model trained on in-domain
data from the popular social network Twitter. TwHIN-BERT differs from prior
pre-trained language models as it is trained with not only text-based
self-supervision, but also with a social objective based on the rich social
engagements within a Twitter heterogeneous information network (TwHIN). Our
model is trained on 7 billion tweets covering over 100 distinct languages
providing a valuable representation to model short, noisy, user-generated text.
We evaluate our model on a variety of multilingual social recommendation and
semantic understanding tasks and demonstrate significant metric improvement
over established pre-trained language models. We will freely open-source
TwHIN-BERT and our curated hashtag prediction and social engagement benchmark
datasets to the research community.

TwHIN-BERT 是一种多语言语言模型，使用来自 Twitter 的专业领域数据进行训练，并通过具有基于 Twitter 异构信息网络（TwHIN）中丰富的社交互动的社交目标的训练使其不同于以前的预训练语言模型。我们在各种多语言社交推荐和语义理解任务上评估了我们的模型，并展示了相对于已建立的预训练语言模型的重大指标改进。