Abstract
Recently, researchers have found that deep LSTMs trained on tasks like machine translation learn substantial syntactic and semantic information about their input sentences, including part-of-speech. These findings begin to shed light on why pretrained representations, like ELMo and CoVe, are so beneficial for neural language understanding models. We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn. With this in mind, we compare four objectives—language modeling, translation, skip-thought, and autoencoding—on their ability to induce syntactic and part-of-speech information, holding constant the quantity and genre of the training data, as well as the LSTM architecture.- Anthology ID:
- W18-5448
- Volume:
- Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
- Month:
- November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Tal Linzen, Grzegorz Chrupała, Afra Alishahi
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 359–361
- Language:
- URL:
- https://aclanthology.org/W18-5448
- DOI:
- 10.18653/v1/W18-5448
- Cite (ACL):
- Kelly Zhang and Samuel Bowman. 2018. Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 359–361, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis (Zhang & Bowman, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/W18-5448.pdf