Abstract
Recent work on data-to-text generation has made progress under the neural encoder-decoder architectures. However, the data input size is often enormous, while not all data records are important for text generation and inappropriate input may bring noise into the final output. To solve this problem, we propose a two-step approach which first selects and orders the important data records and then generates text from the noise-reduced data. Here we propose a learning to rank model to rank the importance of each record which is supervised by a relation extractor. With the noise-reduced data as input, we implement a text generator which sequentially models the input data records and emits a summary. Experiments on the ROTOWIRE dataset verifies the effectiveness of our proposed method in both performance and efficiency.- Anthology ID:
- 2020.ccl-1.82
- Volume:
- Proceedings of the 19th Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2020
- Address:
- Haikou, China
- Editors:
- Maosong Sun (孙茂松), Sujian Li (李素建), Yue Zhang (张岳), Yang Liu (刘洋)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 881–891
- Language:
- English
- URL:
- https://aclanthology.org/2020.ccl-1.82
- DOI:
- Cite (ACL):
- Qianying Liu, Tianyi Li, Wenyu Guan, and Sujian Li. 2020. Refining Data for Text Generation. In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 881–891, Haikou, China. Chinese Information Processing Society of China.
- Cite (Informal):
- Refining Data for Text Generation (Liu et al., CCL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.ccl-1.82.pdf
- Data
- RotoWire