A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization

摘要

Although abstractive summarization models have achieved impressive results on document summarization tasks, their performance on dialogue modeling is much less satisfactory due to the crude and straight methods for dialogue encoding. To address this question, we pro pose a novel end-to-end Transformer-based model FinDS for abstractive dialogue summarization that leverages Finer-grain universal Dialogue semantic Structures to model dialogue and generates better summaries. Experiments on the SAMsum dataset show that FinDS outperforms various dialogue summarization approaches and achieves new state of-the-art (SOTA) ROUGE results. Finally, we apply FinDS to a more complex scenario, showing the robustness of our model. We also release our source code.

会议
EMNLP 2021
雷粤杰
雷粤杰
硕士研究生

生成式对话摘要

郑馥嘉
郑馥嘉
硕士研究生

对话摘要

严渊蒙
严渊蒙
硕士研究生

自然语言理解,预训练

何可清
硕士研究生

对话系统,摘要,预训练

徐蔚然
徐蔚然
副教授,硕士生导师,博士生导师

信息检索,模式识别,机器学习