CLMar 8, 2021

Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data

arXiv:2103.05131v1800 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of quickly obtaining overviews from interleaved discussions for users, though it is incremental as it builds on existing end-to-end and pretraining methods.

The paper tackled the problem of summarizing interleaved texts, such as online chats, by proposing an end-to-end hierarchical encoder-decoder system pretrained with synthetic data, which outperformed a traditional two-step system by 22% on a real-world meeting dataset.

Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions. Existing systems first disentangle the posts by threads and then extract summaries from those threads. A major issue with such systems is error propagation from the disentanglement component. While end-to-end trainable summarization system could obviate explicit disentanglement, such systems require a large amount of labeled data. To address this, we propose to pretrain an end-to-end trainable hierarchical encoder-decoder system using synthetic interleaved texts. We show that by fine-tuning on a real-world meeting dataset (AMI), such a system out-performs a traditional two-step system by 22%. We also compare against transformer models and observed that pretraining with synthetic data both the encoder and decoder outperforms the BertSumExtAbs transformer model which pretrains only the encoder on a large dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes