Telugu - English Dictionary Based Cross Language Query Focused Multi-Document Summarization

Summarization systems and Question Answering systems can be treated to have complementary functionality to each other. For instance, a question answering system could have a summarization module, that can summarize the fragments of answers found by the question answering system. On the other hand a summarization system can be given a question as input, to generate a question focused summary as output [1], [2], [3]. This explanation provides two perspectives of the same coin that are solving a single larger problem of satisfying a user’s given information need in the best possible way. While at first instance this might seem to be a simple fusion of two disciplines, there could be many dimensions to such a task. It can be seen from the roadmap of the summarization research community [7] that, one of the later goals of this area of research is to address not only multi-document, multi-question, summarization tasks, but also to address the multi-lingual dimension apart from many other possible dimensions. In this paper we report our experiments on one such cross lingual multiple document multiple question summarization system with experiments between Telugu, English language pairs. We chose the topics or questions to be in Telugu and the summaries need to be generated from a set of English documents.