TSSuBERT: Tweet Stream Summarization Using BERT
This work addresses the lack of resources and models for tweet summarization, which is incremental as it builds on existing pre-trained language models.
The authors tackled the problem of summarizing tweet streams by introducing a large dataset for Twitter event summarization and proposing an extractive neural model that combines pre-trained language models with frequency-based representations to predict tweet salience, achieving promising results compared to state-of-the-art baselines.
The development of deep neural networks and the emergence of pre-trained language models such as BERT allow to increase performance on many NLP tasks. However, these models do not meet the same popularity for tweet summarization, which can probably be explained by the lack of existing collections for training and evaluation. Our contribution in this paper is twofold : (1) we introduce a large dataset for Twitter event summarization, and (2) we propose a neural model to automatically summarize huge tweet streams. This extractive model combines in an original way pre-trained language models and vocabulary frequency-based representations to predict tweet salience. An additional advantage of the model is that it automatically adapts the size of the output summary according to the input tweet stream. We conducted experiments using two different Twitter collections, and promising results are observed in comparison with state-of-the-art baselines.