Several Studies on Natural Language ·and Back-Propagation

By R. Allen. 1987

Subfields: Natural Language Processing, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Peter J. Liu
2. Quoc V. Le
3. Mohit Bansal
4. Yonatan Belinkov
5. Mirella Lapata
6. Jianfeng Gao
7. Prajit Ramachandran
8. Luke S. Zettlemoyer

In Optimization & Training

1. Prajit Ramachandran
2. Jordan B. Pollack
3. Lonnie Chrisman
4. Quoc V. Le
5. Peter J. Liu
6. Barret Zoph
7. Frank Hutter
8. Xuanyi Dong

Citations in the corpus

• Unsupervised Pretraining for Sequence to Sequence Learning (2016, background): “Sequence to sequence (seq2seq) models (Sutskever et al., 2014; Cho et al., 2014; Kalchbrenner and Blunsom, 2013; Allen, 1987; Ñeco and Forcada, 1997) are extremely effective on a variety of tasks that require a mapping between a variable-length input sequence to a variable-length output sequence.”
• Learning Recursive Distributed Representations for Holistic Computation (1991, background): “In fact, [Allen, 1987] reports also encountering this same phenomena.”
• Recursive Distributed Representations (1990, background): “Both early connectionist work, such as McClelland & Rumelhart’s word recognition model [13], as well as more modern efforts [4, 14] use this approach, which is not able to represent or process sequences longer than a predetermined bound.”