Paper: A System for Summarizing Scientific Topics Starting from Keywords

ACL ID P13-2102
Title A System for Summarizing Scientific Topics Starting from Keywords
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

In this paper, we investigate the problem of automatic generation of scientific sur- veys starting from keywords provided by a user. We present a system that can take a topic query as input and generate a sur- vey of the topic by first selecting a set of relevant documents, and then selecting relevant sentences from those documents. We discuss the issues of robust evalua- tion of such systems and describe an eval- uation corpus we generated by manually extracting factoids, or information units, from 47 gold standard documents (surveys and tutorials) on seven topics in Natural Language Processing. We have manually annotated 2,625 sentences with these fac- toids (around 375 sentences per topic) to build an evaluation corpus for this task. We present evaluation results for the per- formance o...