Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
By Samuel R. Bowman, Ellie Pavlick, Edouard Grave, Benjamin Van Durme, Alex Wang, Jan Hula, Patrick Xia, Raghavendra Reddy Pappagari, R. Thomas McCoy, Roma Patel and 6 more. 2018
28 citations recorded by the source corpus.
Work on the problem of contextualized word representation---the development of reusable neural network components for sentence understanding---has recently seen a surge of progress centered on the unsupervised pretraining task of language modeling with methods like ELMo. This paper contributes the first large-scale systematic study comparing different pretraining tasks in this context, both as complements to language modeling and as potential alternatives. The primary results of the study support the use of language modeling as a pretraining task and set a new state of the art among comparable models using multitask learning with language models. However, a closer look at these results reveals worryingly strong baselines and strikingly varied results across target tasks, suggesting that the widely-used paradigm of pretraining and freezing sentence encoders may not be an ideal platform for further work.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Felix Stahlberg
- Luke S. Zettlemoyer
- Quoc V. Le
- Alec Radford
- Mohit Bansal
- Yoshua Bengio
- Kyunghyun Cho
- Sergey Levine
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Felix Stahlberg
- Trevor Darrell
- Xiaogang Wang
- Andrea Vedaldi
- Jitendra Malik
In Natural Language Processing
In Representation & Self-Supervised Learning
Citations in the corpus
- Language Models are Unsupervised Multitask Learners (2019, background): “Recent work reports modest performance improvements (Yogatama et al., 2019) and the two most ambitious efforts to date have trained on a total of 10 and 17 (dataset, objective) pairs respectively (McCann et al., 2018) (Bowman et al., 2018).”
- Neural Machine Translation: A Review (2019, background): “Contextualized word embeddings have advanced the state-of-the-art in several NLP benchmarks (Peters et al., 2018; Bowman et al., 2018; Devlin et al., 2019).”