arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.07786cs.CLcs.AI
收藏

标题生成的自注意模型

Self-Attentive Model for Headline Generation

Daniil Gavrilov, Pavel Kalaidin, Valentin Malykh

摘要:

标题生成是一种特殊类型的文本摘要任务。虽然这个任务的可用训练数据量几乎是无限的,但它仍然具有挑战性,因为学习为新闻文章生成标题意味着模型对自然语言有很强的推理能力。为了克服这个问题,我们应用了最近的通用Transformer架构与字节对编码技术配对,并在纽约时报注释语料库上获得了新的最先进的结果,ROUGE-L F1得分为24.84,ROUGE-2 F1得分为13.48。我们还介绍了新的RIA语料库,并达到ROUGE-L的F1-评分36.81和ROUGE-2的F1-评分22.15。

英文摘要:

Headline generation is a special type of text summarization task. While the amount of available training data for this task is almost unlimited, it still remains challenging, as learning to generate headlines for news articles implies that the model has strong reasoning about natural language. To overcome this issue, we applied recent Universal Transformer architecture paired with byte-pair encoding technique and achieved new state-of-the-art results on the New York Times Annotated corpus with ROUGE-L F1-score 24.84 and ROUGE-2 F1-score 13.48. We also present the new RIA corpus and reach ROUGE-L F1-score 36.81 and ROUGE-2 F1-score 22.15 on it.

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。

↑