Abstract
We examine the task of aggregation in the context of text-to-text generation. We introduce a new aggregation task which frames the process as grouping input sentence fragments into clusters that are to be expressed as a single output sentence. We extract datasets for this task from a corpus using an automatic extraction process. Based on the results of a user study, we develop two gold-standard clusterings and corresponding evaluation methods for each dataset. We present a hierarchical clustering framework for predicting aggregation decisions on this task, which outperforms several baselines and can serve as a reference in future work.- Anthology ID:
- C16-1101
- Volume:
- Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Yuji Matsumoto, Rashmi Prasad
- Venue:
- COLING
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 1061–1070
- Language:
- URL:
- https://aclanthology.org/C16-1101
- DOI:
- Cite (ACL):
- Victor Chenal and Jackie Chi Kit Cheung. 2016. Predicting sentential semantic compatibility for aggregation in text-to-text generation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1061–1070, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Predicting sentential semantic compatibility for aggregation in text-to-text generation (Chenal & Cheung, COLING 2016)
- PDF:
- https://preview.aclanthology.org/naacl24-info/C16-1101.pdf