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 2403.05101cs.CLcs.AI
收藏

规则驱动的新闻标题生成

Rule-driven News Captioning

School of Electrical and Information Engineering, Tianjin University(天津大学电气与信息工程学院)

Ning Xu, Tingting Zhang, Hongshuo Tian, An-An Liu

AI总结:

本文提出规则驱动的新闻标题生成方法,通过设计新闻感知语义规则并注入BART模型,引导生成符合新闻报道规则的图像描述,在GoodNews和NYTimes800k数据集上验证了有效性。

摘要:

新闻标题生成任务旨在通过描述图像中的命名实体或具体事件,结合其新闻文章来生成句子。现有方法通过依赖大规模预训练模型取得了显著成果,这些模型主要关注输入新闻内容与输出预测之间的相关性。然而,新闻标题生成需要遵循新闻报道的一些基本规则,例如准确描述与事件相关的个体和行动。在本文中,我们提出了规则驱动的新闻标题生成方法,该方法能够按照指定的规则信号生成图像描述。具体来说,我们首先为描述设计了新闻感知的语义规则。该规则包含了图像中描绘的主要动作(例如“执行”)以及参与该动作的命名实体所扮演的角色(例如“主体”和“地点”)。其次,我们通过前缀调整策略将该语义规则注入到大规模预训练模型BART中,其中多个编码器层嵌入了新闻感知的语义规则。最后,我们能够有效地引导BART生成符合指定规则的新闻句子。在两个广泛使用的数据集(即GoodNews和NYTimes800k)上进行的大量实验证明了我们方法的有效性。

英文摘要:

News captioning task aims to generate sentences by describing named entities or concrete events for an image with its news article. Existing methods have achieved remarkable results by relying on the large-scale pre-trained models, which primarily focus on the correlations between the input news content and the output predictions. However, the news captioning requires adhering to some fundamental rules of news reporting, such as accurately describing the individuals and actions associated with the event. In this paper, we propose the rule-driven news captioning method, which can generate image descriptions following designated rule signal. Specifically, we first design the news-aware semantic rule for the descriptions. This rule incorporates the primary action depicted in the image (e.g., "performing") and the roles played by named entities involved in the action (e.g., "Agent" and "Place"). Second, we inject this semantic rule into the large-scale pre-trained model, BART, with the prefix-tuning strategy, where multiple encoder layers are embedded with news-aware semantic rule. Finally, we can effectively guide BART to generate news sentences that comply with the designated rule. Extensive experiments on two widely used datasets (i.e., GoodNews and NYTimes800k) demonstrate the effectiveness of our method.

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。

↑