TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter
This addresses the need for better language models for noisy, user-generated text on social media platforms like Twitter, though it is incremental as it builds on existing PLM frameworks with added social data.
The authors tackled the problem of pre-trained language models not being tailored to noisy social media text by introducing TwHIN-BERT, a multilingual model trained on 7 billion tweets with social engagement objectives, which showed significant metric improvements on multilingual social recommendation and semantic understanding tasks.
Pre-trained language models (PLMs) are fundamental for natural language processing applications. Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network. We present TwHIN-BERT, a multilingual language model productionized at Twitter, trained on in-domain data from the popular social network. 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 various multilingual social recommendation and semantic understanding tasks and demonstrate significant metric improvement over established pre-trained language models. We open-source TwHIN-BERT and our curated hashtag prediction and social engagement benchmark datasets to the research community.