Transfer Learning and Masked Generation for Answer Verbalization
Sebastien Montella, Lina Rojas-Barahona, Frederic Bechet, Johannes Heinecke, Alexis Nasr
Abstract
Structured Knowledge has recently emerged as an essential component to support fine-grained Question Answering (QA). In general, QA systems query a Knowledge Base (KB) to detect and extract the raw answers as final prediction. However, as lacking of context, language generation can offer a much informative and complete response. In this paper, we propose to combine the power of transfer learning and the advantage of entity placeholders to produce high-quality verbalization of extracted answers from a KB. We claim that such approach is especially well-suited for answer generation. Our experiments show 44.25%, 3.26% and 29.10% relative gain in BLEU over the state-of-the-art on the VQuAnDA, ParaQA and VANiLLa datasets, respectively. We additionally provide minor hallucinations corrections in VANiLLa standing for 5% of each of the training and testing set. We witness a median absolute gain of 0.81 SacreBLEU. This strengthens the importance of data quality when using automated evaluation.- Anthology ID:
- 2022.suki-1.6
- Volume:
- Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, USA
- Editors:
- Wenhu Chen, Xinyun Chen, Zhiyu Chen, Ziyu Yao, Michihiro Yasunaga, Tao Yu, Rui Zhang
- Venue:
- SUKI
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 47–54
- Language:
- URL:
- https://aclanthology.org/2022.suki-1.6
- DOI:
- 10.18653/v1/2022.suki-1.6
- Cite (ACL):
- Sebastien Montella, Lina Rojas-Barahona, Frederic Bechet, Johannes Heinecke, and Alexis Nasr. 2022. Transfer Learning and Masked Generation for Answer Verbalization. In Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI), pages 47–54, Seattle, USA. Association for Computational Linguistics.
- Cite (Informal):
- Transfer Learning and Masked Generation for Answer Verbalization (Montella et al., SUKI 2022)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2022.suki-1.6.pdf
- Data
- ParaQA, VANiLLa