TWAG: A Topic-Guided Wikipedia Abstract Generator

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 4623–4635 August 1–6, 2021. ©2021 Association for Computational Linguistics 4623 TWAG: A Topic-guided Wikipedia Abstract Generator Fangwei Zhu1,2, Shangqing Tu3, Jiaxin Shi1,2, Juanzi Li1,2, Lei Hou1,2∗ and Tong Cui4 1Dept. of Computer Sci.&Tech., BNRist, Tsinghua University, Beijing 100084, China 2KIRC, Institute for Artificial Intelligence, Tsinghua University 3School of Computer Science and Engineering, Beihang University 4Noah’s Ark Lab, Huawei Inc. {zfw19@mails.,shijx16@mails,lijuanzi@,houlei@}tsinghua.edu.cn tsq@buaa.edu.cn,cuitong5@huawei.com Abstract Wikipedia abstract generation aims to distill a Wikipedia abstract from web sources and has met significant success by adopting multi- document summarization techniques. How- ever, previous works generally view the ab- stract as plain text, ignoring the fact that it is a description of a certain entity and can be decomposed into different topics. In this pa- per, we propose a two-stage model TWAG that guides the abstract generation with topical in- formation. First, we detect the topic of each input paragraph with a classifier trained on ex- isting Wikipedia articles to divide input docu- ments into different topics. Then, we predict the topic distribution of each abstract sentence, and decode the sentence from topic-aware representations with a Pointer-Generator net- work. We evaluate our model on the Wi- kiCatSum dataset, and the results show that TWAG outperforms various existing baselines and is capable of generating comprehensive ab- stracts. Our code and dataset can be accessed at https://github.com/THU-KEG/TWAG 1 Introduction Wikipedia, one of the most popular crowd-sourced online knowledge bases, has been widely used as the valuable resources in natural language process- ing tasks such as knowledge acquisition (Lehmann et al., 2015) and question answering (Hewlett et al., 2016; Rajpurkar et al., 2016) due to its high qual- ity and wide coverage. Within a Wikipedia article, its abstract is the overview of the whole content, and thus becomes the most frequently used part in various tasks. However, the abstract is often con- tributed by experts, which is labor-intensive and prone to be incomplete. In this paper, we aim to automatically generate Wikipedia abstracts based on the related documents ∗ Corresponding Author collected from referred websites or search engines, which is essentially a multi-document summariza- tion problem. This problem is studied in both ex- tractive and abstractive manners. The extractive models attempt to select relevant textual units from input documents and combine them into a summary. Graph-based representations are widely exploited to capture the most salient tex- tual units and enhance the quality of the final sum- mary (Erkan and Radev, 2004; Mihalcea and Tarau, 2004; Wan, 2008). Recently, there also emerge neural extractive models (Yasunaga et al., 2017; Yin et al., 2019) utilizing the graph convolutional network (Kipf and Welling, 2017) to better capture inter-document relations. However, these models are not suitable for Wikipedia abstract generation. The reason is that the input documents collected from various sources are often noisy and lack intrin- sic relations (Sauper and Barzilay, 2009), which makes the relation graph hard to …

Content truncated to 500 words