- 期刊
- OpenAccess
Augmented Abstractive Summarization with Document-Level Semantic Graph
摘要
Previous abstractive methods apply sequence-to-sequence structures to generate summary without a module to assist the system to detect vital mentions and relationships within a document. To address this problem, we utilize semantic graph to boost the generation performance. Firstly, we extract important entities from each document and then establish a graph inspired by the idea of distant supervision (Mintz et al., 2009). Then, we combine a Bi-LSTM with a graph encoder to obtain the representation of each graph node. A novel neural decoder is presented to leverage the information of such entity graphs. Automatic and human evaluations show the effectiveness of our technique.
延伸閱讀
- Wang, W. C. (2021). Semantic Similarity Detection for Legal Texts Between Act and Direction [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU202102272
- Cheung, K. M. (2002). Efficient algorithms for semantic net construction and maintenance [master's thesis, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200006338
- Chen, Y. J. (2012). A Text Summarization Model based on Genetic Algorithm [master's thesis, National Tsing Hua University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0016-0908201218211963
- YANG, C. Z., FAN, J. S., & LIU, Y. F. (2016). Multi-document Summarization using Probabilistic Topic-based Network Models. Journal of Information Science and Engineering, 32(6), 1613-1634. https://www.airitilibrary.com/Article/Detail?DocID=10162364-201611-201703280017-201703280017-1613-1634
- Chang, C. T. (2018). A Hybrid Word-Character Approach to Abstractive Summarization [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU201801093