arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.10967cs.CL
收藏

聚类模式学习在摘要生成中的应用

Learning Cluster Patterns for Abstractive Summarization

Kunsan National University(群山国立大学);Yonsei University(延世大学)

Sung-Guk Jo, Jeong-Jae Kim, Byung-Won On

摘要:

如今,预训练的序列到序列模型,如BERTSUM和BART,在抽象摘要方面已经显示出最先进的结果。在这些模型中,在微调期间,编码器将句子转换为潜在空间中的上下文向量,解码器基于上下文向量学习摘要生成任务。在我们的方法中,我们考虑两个集群的显着和非显着的上下文向量,使用它的解码器可以参加更多的显着上下文向量摘要生成。为此,我们提出了一种新的聚类Transformer层之间的编码器和解码器,它首先生成两个集群的显着和非显着的向量,然后规范化和收缩的集群,使它们分开的潜在空间。我们的实验结果表明,该模型优于现有的BART模型,通过学习这些不同的聚类模式,提高高达4%的ROUGE和0.3%的BERTScore平均在CNN/DailyMail和XSUM数据集。

英文摘要:

Nowadays, pre-trained sequence-to-sequence models such as BERTSUM and BART have shown state-of-the-art results in abstractive summarization. In these models, during fine-tuning, the encoder transforms sentences to context vectors in the latent space and the decoder learns the summary generation task based on the context vectors. In our approach, we consider two clusters of salient and non-salient context vectors, using which the decoder can attend more to salient context vectors for summary generation. For this, we propose a novel clustering transformer layer between the encoder and the decoder, which first generates two clusters of salient and non-salient vectors, and then normalizes and shrinks the clusters to make them apart in the latent space. Our experimental result shows that the proposed model outperforms the existing BART model by learning these distinct cluster patterns, improving up to 4% in ROUGE and 0.3% in BERTScore on average in CNN/DailyMail and XSUM data sets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑