Empirically designing and evaluating a new revision-based model for summary generation
Artificial Intelligence - Special volume on empirical methods
A computational theory of perspective and reference in narrative
ACL '88 Proceedings of the 26th annual meeting on Association for Computational Linguistics
Enriching the knowledge sources used in a maximum entropy part-of-speech tagger
EMNLP '00 Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Non-textual event summarization by applying machine learning to template-based language generation
UCNLG+Sum '09 Proceedings of the 2009 Workshop on Language Generation and Summarisation
Detecting interesting event sequences for sports reporting
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
Perspective-oriented generation of football match summaries: Old tasks, new challenges
ACM Transactions on Speech and Language Processing (TSLP)
| Hi-index | 0.00 |
This paper presents a reordering algorithm for generating multiple stories from different perspectives based on a single baseball game. We take a description of a game and a neutral summary, reorder the content of the neutral summary based on event features, and produce two summaries that the users rated as showing perspectives of each of the two teams. We describe the results from an initial user survey that revealed the power of reordering on the users' perception of perspective. Then we describe our reordering algorithm which was derived from analyzing the corpus of local newspaper articles of teams involved in the games as well as a neutral corpus for the respective games. The resulting reordering algorithm is successful at turning a neutral article into two different summary articles that express the two teams' perspectives.