Elamur Research⌕
☰
home / authors / Peter Shaw

Peter Shaw

Peter Shaw has 2 papers in our library, in 2018–2022; often with Ashish Vaswani, Jakob Uszkoreit, Kristina Toutanova.

2 papers in our library · 2018–2022

OpenAlex · ORCID · Wikidata · h-index 39 · 190 works · 8,405 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 467 times in our library · ⭐ Paper Stars ranking: #962

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Wenzhou Medical UniversityWenzhou · China2024–2026 · 9 paperscurrent🎓Yantai UniversityYantai · China2026 · 1 papercurrent🏢Merck & Co., Inc., Rahway, NJ, USARahway · United States2006–2023 · 32 papers🎓Nanjing University of Information Science and TechnologyNanjing · China2020–2022 · 21 papersEmployment since 2022🏢GoogleMountain View · United States2018–2022 · 13 papers🏢Bristol-Myers SquibbNew York · United States1998–2007 · 12 papers🤝Menzies School of Health ResearchDarwin · Australia2020–2022 · 10 papers🎓Massey UniversityPalmerston North · New Zealand2018–2019 · 9 papers🎓New York UniversityNew York · United States1991–1998 · 8 papers🏢Ferring PharmaceuticalsMiami · United States2017–2020 · 7 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 26 more institutions on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Transformer and attention · 1 work

 Works by year

2020s

20221 paperImproving Compositional Generalization with Latent Structure and Data Augmentation

2010s

20181 paperSelf-Attention with Relative Position Representations

 Papers

The most cited first (OpenAlex and our library).

  1. Self-Attention with Relative Position Representations (2018 · 2,820 citations)
    The Transformer uses neither recurrence nor convolution, so it has no built-in sense of token order. The original model compensates by adding sinusoidal encodings of absolute positions to its inputs. Shaw, Uszkoreit and Vaswani instead build order information directly into self-attention. They treat the input as a…
  2. Improving Compositional Generalization with Latent Structure and Data Augmentation (2022 · 76 citations)
    Pre-trained sequence-to-sequence models such as T5 cope well with natural language variation. However, they often fail when test inputs combine familiar elements in unseen ways. Specialized models with discrete latent structure handle such compositions better, but their gains have mostly been limited to synthetic…

 Co-authors here

7 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 467 times (of the 141,840 papers whose bibliographies we read); 44 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/peter-shaw/