Evaluating Image-Inspired Poetry Generation

扫码查看

原文链接

NETL
Springer Nature

外文摘要：Creative natural language generation， such as poetry generation， writing lyrics， and storytelling， is appealing but difficult to evaluate。 We take the application of image-inspired poetry generation as a showcase and investigate two problems in evaluation: (1) how to evaluate the generated text when there are no ground truths， and (2) how to evaluate nondeterministic systems that output different texts given the same input image。 Regarding the first problem， we first design a judgment tool to collect ratings of a few poems for comparison with the inspiring image shown to assessors。 We then propose a novelty measurement that quantifies how different a generated text is compared to a known corpus。 Regarding the second problem， we experiment with different strategies to approximate evaluating multiple trials of output poems。 We also use a measure for quantifying the diversity of different texts generated in response to the same input image， and discuss their merits。

外文关键词：

EvaluationPoetry generationNatural language generationAl-based creationImage

作者：

Chao-Chung Wu、Ruihua Song、Tetsuya Sakai、Wen-Feng Cheng、Xing Xie、Shou-De Lin

展开 >

作者单位：

National Taiwan University, Taipei, Taiwan

Microsoft Xialce, Beijing, China

Waseda University, Tokyo, Japan

Microsoft Research Asia, Beijing, China

展开 >

会议名称：

CCF international conference on natural language processing and Chinese computing

会议地点：

Dunhuang(CN)

会议母体文献：

Natural language processing and Chinese computing

页码：

539-551

出版时间：

2019

DOI：

10.1007/978-3-030-32233-5_42