Abstract
In this paper, we model the document revision detection problem as a minimum cost branching problem that relies on computing document distances. Furthermore, we propose two new document distance measures, word vector-based Dynamic Time Warping (wDTW) and word vector-based Tree Edit Distance (wTED). Our revision detection system is designed for a large scale corpus and implemented in Apache Spark. We demonstrate that our system can more precisely detect revisions than state-of-the-art methods by utilizing the Wikipedia revision dumps and simulated data sets.- Anthology ID:
- I17-1095
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 947–956
- Language:
- URL:
- https://aclanthology.org/I17-1095
- DOI:
- Cite (ACL):
- Xiaofeng Zhu, Diego Klabjan, and Patrick Bless. 2017. Semantic Document Distance Measures and Unsupervised Document Revision Detection. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 947–956, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Semantic Document Distance Measures and Unsupervised Document Revision Detection (Zhu et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/I17-1095.pdf
- Code
- XiaofengZhu/wDTW-wTED