Abstract
Language models have demonstrated the ability to generate highly fluent text; however, it remains unclear whether their output retains coherent high-level structure (e.g., story progression). Here, we propose to apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of the generated text. Model criticism compares the distributions between real and generated data in a latent space obtained according to an assumptive generative process. Different generative processes identify specific failure modes of the underlying model. We perform experiments on three representative aspects of high-level discourse—coherence, coreference, and topicality—and find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.- Anthology ID:
- 2022.emnlp-main.815
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11887–11912
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.815
- DOI:
- 10.18653/v1/2022.emnlp-main.815
- Cite (ACL):
- Yuntian Deng, Volodymyr Kuleshov, and Alexander Rush. 2022. Model Criticism for Long-Form Text Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11887–11912, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Model Criticism for Long-Form Text Generation (Deng et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.emnlp-main.815.pdf