Compressive approaches for cross-language multi-document summarization

The popularization of social networks and digital documents has quickly increased the multilingual information available on the Internet. However, this huge amount of data cannot be analyzed manually. This paper deals with Cross-Language Text Summarization (CLTS) that produces a summary in a different language from the source documents. We describe three compressive CLTS approaches that analyze the text in the source and target languages to compute the relevance of sentences. Our systems compress sentences at two levels: clusters of similar sentences are compressed using a multi-sentence compression (MSC) method and single sentences are compressed using a Neural Network model. The version of our approach using multi-sentence compression generated more informative French-to-English cross-lingual summaries than extractive state-of-the-art systems. Moreover, these cross-lingual summaries have a grammatical quality similar to extractive approaches.