Abstract
In this paper, we introduce our Tokyo Metropolitan University Feedback Comment Generation system submitted to the feedback comment generation task for INLG 2023 Generation Challenge. In this task, a source sentence and offset range of preposition uses are given as the input. Then, a system generates hints or explanatory notes about preposition uses as the output. To tackle this generation task, we finetuned pretrained sequence-to-sequence language models. The models using BART and T5 showed significant improvement in BLEU score, demonstrating the effectiveness of the pretrained sequence-to-sequence language models in this task. We found that using part-of-speech tag information as an auxiliary input improves the generation quality of feedback comments. Furthermore, we adopt a simple postprocessing method that can enhance the reliability of the generation. As a result, our system achieved the F1 score of 47.4 points in BLEU-based evaluation and 60.9 points in manual evaluation, which ranked second and third on the leaderboard.- Anthology ID:
- 2023.inlg-genchal.10
- Volume:
- Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editor:
- Simon Mille
- Venues:
- INLG | SIGDIAL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 68–73
- Language:
- URL:
- https://aclanthology.org/2023.inlg-genchal.10
- DOI:
- Cite (ACL):
- Naoya Ueda and Mamoru Komachi. 2023. TMU Feedback Comment Generation System Using Pretrained Sequence-to-Sequence Language Models. In Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges, pages 68–73, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- TMU Feedback Comment Generation System Using Pretrained Sequence-to-Sequence Language Models (Ueda & Komachi, INLG-SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/2023.inlg-genchal.10.pdf