Auto-hMDS: Automatic Construction of a Large Heterogeneous Multilingual Multi-Document Summarization Corpus

Automatic text summarization is a challenging natural language processing (NLP) task which has been researched for several decades. The available datasets for multi-document summarization (MDS) are, however, rather small and usually focused on the newswire genre. Nowadays, machine learning methods are applied to more and more NLP problems such as machine translation, question answering, and single-document summarization. Modern machine learning methods such as neural networks require large training datasets which are available for the three tasks but not yet for MDS. This lack of training data limits the development of machine learning methods for MDS. In this work, we automatically generate a large heterogeneous multilingual multi-document summarization corpus. The key idea is to use Wikipedia articles as summaries and to automatically search for appropriate source documents. We created a corpus with 7,316 topics in English and German, which has variing summary lengths and variing number of source documents. More information about the corpus can be found at the corpus GitHub page at https://github.com/AIPHES/auto-hMDS .