🧑‍🔬 Miltiadis Allamanis

🏛️ Affiliations

🏢Microsoft ResearchCambridge · United Kingdom2016–2023 · 21 papers🏢MicrosoftRedmond · United States2017–2022 · 17 papers🎓University of EdinburghEdinburgh · United Kingdom2013–2021 · 13 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search (2020 · 656 citations)
   Finding code from a natural-language request is difficult. Programmers name things with terse, technical identifiers, while queries describe intent loosely, so the two often share few words. The field also lacked a sizeable benchmark built for this task. The authors address both gaps with two resources.
2. The Adverse Effects of Code Duplication in Machine Learning Models of Code (2018 · 319 citations)
   The paper studies how code duplication in large corpora (primarily those collected from GitHub) distorts the training and evaluation of machine learning models for code in the "big code" field.
3. A Convolutional Attention Network for Extreme Summarization of Source Code (2016 · 198 citations)
   The authors study "extreme" summarization of source code. The model receives only the tokens of a code snippet, such as the body of a Java method, and must generate a short, meaningful name that resembles a function name. Earlier approaches depended on predefined features, such as the signature or the class. This…
4. A Survey of Machine Learning for Big Code and Naturalness (2017 · 167 citations)
   This survey maps out a young field that applies machine learning to source code. It is framed by the "naturalness hypothesis": code is written by people for people, so large code corpora show statistical regularities similar to those in natural language, and tools can exploit them. The authors (Microsoft Research…
5. Learning to Represent Programs with Graphs (2017 · 127 citations)
   The authors argue that most neural networks for code analysis treat code like ordinary text, either as a sequence of tokens or as a syntax tree.

All works

13 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. CodeSearchNet Challenge: Evaluating the State of Semantic Code SearcharXiv:1909.09436Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, et al.2020 · 656 citations
2. The Adverse Effects of Code Duplication in Machine Learning Models of CodearXiv:1812.06469Miltiadis Allamanis2018 · 319 citations
3. A Convolutional Attention Network for Extreme Summarization of Source CodearXiv:1602.03001Miltiadis Allamanis, Hao Peng, Charles Sutton2016 · 198 citations
4. Mining Idioms from Source Code ↗arXiv:1404.0417 · no summary yetMiltiadis Allamanis, Charles Sutton2014 · 180 citations
5. Bimodal Modelling of Source Code and Natural Language ↗ICML 2015, PMLR 37:2123–2132 · no summary yetMiltos Allamanis et al.2015 · 179 citations
6. A Survey of Machine Learning for Big Code and NaturalnessACM Computing SurveysMiltiadis Allamanis, Earl T. Barr, Premkumar Devanbu, et al.2017 · 167 citations
7. Learning to Represent Programs with GraphsarXiv:1711.00740Miltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi2017 · 127 citations
8. DIRE: A Neural Approach to Decompiled Identifier Naming ↗IEEE/ACM International Conference on Automated Software Engineering (ASE) · no summary yetJeremy Lacomis et al.2019 · 102 citations
9. Learning to Represent Edits ↗arXiv:1810.13337 · no summary yetPengcheng Yin et al.2018 · 91 citations
10. Learning Continuous Semantic Representations of Symbolic Expressions ↗arXiv:1611.01423 · no summary yetMiltiadis Allamanis et al.2016 · 57 citations
11. Self-Supervised Bug Detection and Repair ↗arXiv:2105.12787 · no summary yetMiltiadis Allamanis, Henry Jackson-Flux, Marc Brockschmidt2021 · 50 citations
12. NExT: Teaching Large Language Models to Reason about Code Execution ↗arXiv:2404.14662 · no summary yetAnsong Ni et al.2024 · 30 citations
13. Modelling Natural Language, Programs, and their Intersection ↗Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts · no summary yetGraham Neubig, Miltiadis Allamanis2018 · 4 citations

🤝 Co-authors here

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

• Charles Sutton ×2
• Marc Brockschmidt ×2
• Hao Peng
• Mahmoud Khademi

Venues

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

• ACM Computing Surveys: ACM Computing Surveys 2017
• ICML 2015, PMLR 37:2123–2132
• IEEE/ACM International Conference on Automated Software Engineering (ASE)
• Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts

🔗 Cited by

Papers of our library cite their works 2,877 times (of the 149,439 papers whose bibliographies we read); 659 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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