This post is a reminder of the papers that I have read and am going to read recently.
- The papers that I haven’t finished reading:
- Rogers, Anna, Olga Kovaleva, and Anna Rumshisky. “A primer in bertology: What we know about how bert works.” Transactions of the Association for Computational Linguistics 8 (2020): 842-866.
- The papers that I am going to read:
Bouraoui, Zied, Jose Camacho-Collados, and Steven Schockaert. “Inducing relational knowledge from BERT.” Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34. No. 05. 2020.
Yao, Huihan, et al. “Refining Neural Networks with Compositional Explanations.” arXiv preprint arXiv:2103.10415 (2021).
- Jiang, Zhengbao, et al. “How can we know what language models know?.” Transactions of the Association for Computational Linguistics 8 (2020): 423-438.
- generate or select better prompt to retrieval knowledge from LMs
- Talmor, Alon, et al. “oLMpics–On what Language Model Pre-training Captures.” arXiv preprint arXiv:1912.13283 (2019).
- The papers that I have read:
Yin, Da, Tao Meng, and Kai-Wei Chang. “Sentibert: A transferable transformer-based architecture for compositional sentiment semantics.” arXiv preprint arXiv:2005.04114 (2020).
Petroni, Fabio, et al. “Language models as knowledge bases?.” arXiv preprint arXiv:1909.01066 (2019). - it is non-trivial to extract a knowl- edge base from text that performs on par to di- rectly using pretrained BERT-large.