Melvin Johnson

11.5k total citations · 1 hit paper
15 papers, 1.6k citations indexed

About

Melvin Johnson is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Infectious Diseases. According to data from OpenAlex, Melvin Johnson has authored 15 papers receiving a total of 1.6k indexed citations (citations by other indexed papers that have themselves been cited), including 15 papers in Artificial Intelligence, 6 papers in Computer Vision and Pattern Recognition and 0 papers in Infectious Diseases. Recurrent topics in Melvin Johnson's work include Natural Language Processing Techniques (14 papers), Topic Modeling (13 papers) and Multimodal Machine Learning Applications (6 papers). Melvin Johnson is often cited by papers focused on Natural Language Processing Techniques (14 papers), Topic Modeling (13 papers) and Multimodal Machine Learning Applications (6 papers). Melvin Johnson collaborates with scholars based in United States, United Kingdom and Israel. Melvin Johnson's co-authors include Orhan Fırat, Yonghui Wu, Zhifeng Chen, Mike Schuster, Jay B. Dean, Quoc V. Le, Maxim Krikun, Greg S. Corrado, Macduff Hughes and Nikhil Thorat and has published in prestigious journals such as Transactions of the Association for Computational Linguistics, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) and International Conference on Machine Learning.

In The Last Decade

Melvin Johnson

15 papers receiving 1.5k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

2017 896 citations Melvin Johnson, Mike Schuster et al. Transactions of the Association for Computational Linguistics profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Melvin Johnson United States	9	1.4k	582	71	67	47	15	1.6k
Marjan Ghazvininejad United States	15	1.1k 0.8×	421 0.7×	78 1.1×	51 0.8×	34 0.7×	32	1.3k
Nikhil Thorat United States	3	839 0.6×	425 0.7×	47 0.7×	38 0.6×	37 0.8×	5	1.0k
Matt Post United States	21	1.9k 1.3×	361 0.6×	132 1.9×	51 0.8×	82 1.7×	69	2.0k
Manfred Pinkal Germany	19	990 0.7×	563 1.0×	81 1.1×	79 1.2×	22 0.5×	58	1.5k
Naman Goyal United States	10	1.1k 0.8×	270 0.5×	69 1.0×	135 2.0×	40 0.9×	26	1.2k
Loïc Barrault France	11	1.4k 1.0×	405 0.7×	158 2.2×	52 0.8×	75 1.6×	36	1.6k
Masaaki Nagata Japan	22	1.7k 1.2×	273 0.5×	135 1.9×	30 0.4×	59 1.3×	161	1.8k
Marta R. Costa‐jussà Spain	18	1.6k 1.1×	347 0.6×	112 1.6×	35 0.5×	80 1.7×	149	1.7k
Macduff Hughes United States	2	805 0.6×	362 0.6×	42 0.6×	29 0.4×	36 0.8×	3	933
Radu Soricut United States	17	2.0k 1.4×	1.2k 2.0×	187 2.6×	43 0.6×	69 1.5×	42	2.5k

Countries citing papers authored by Melvin Johnson

Since Specialization

Citations

This map shows the geographic impact of Melvin Johnson's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Melvin Johnson with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Melvin Johnson more than expected).

Fields of papers citing papers by Melvin Johnson

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Melvin Johnson. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Melvin Johnson. The network helps show where Melvin Johnson may publish in the future.

Co-authorship network of co-authors of Melvin Johnson

This figure shows the co-authorship network connecting the top 25 collaborators of Melvin Johnson. A scholar is included among the top collaborators of Melvin Johnson based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Melvin Johnson. Melvin Johnson is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

15 of 15 papers shown

1.

Zhang, Biao, et al.. (2022). Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 4176–4192. 3 indexed citations

2.

Siddhant, Aditya, et al.. (2022). DOCmT5: Document-Level Pretraining of Multilingual Language Models. 425–437. 3 indexed citations

3.

Conneau, Alexis, Ankur Bapna, Yu Zhang, et al.. (2022). XTREME-S: Evaluating Cross-lingual Speech Representations. Interspeech 2022. 3248–3252. 10 indexed citations

4.

Chakravarthi, Bharathi Raja, et al.. (2021). Findings of the Shared Task on Machine Translation in Dravidian languages. 119–125. 5 indexed citations

5.

Khanuja, Simran, Melvin Johnson, & Partha Talukdar. (2021). MergeDistill: Merging Language Models using Pre-trained Distillation. 2874–2887. 4 indexed citations

6.

Kale, Mihir, Aditya Siddhant, Rami Al‐Rfou, et al.. (2021). nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?. 683–691. 7 indexed citations

7.

Johnson, Melvin, et al.. (2021). HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 6 indexed citations

8.

Hu, Junjie, Melvin Johnson, Orhan Fırat, Aditya Siddhant, & Graham Neubig. (2021). Explicit Alignment Objectives for Multilingual Bidirectional Encoders. 3633–3643. 30 indexed citations

9.

Hu, Junjie, Sebastian Ruder, Aditya Siddhant, et al.. (2020). XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation. International Conference on Machine Learning. 1. 4411–4421. 202 indexed citations

10.

Ye, Jia, Melvin Johnson, Wolfgang Macherey, et al.. (2019). Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation. 7180–7184. 81 indexed citations

11.

Aharoni, Roee, Melvin Johnson, & Orhan Fırat. (2019). Massively Multilingual Neural Machine Translation. 3874–3884. 211 indexed citations

12.

Ye, Jia, Ron J. Weiss, Fadi Biadsy, et al.. (2019). Direct Speech-to-Speech Translation with a Sequence-to-Sequence Model. 1123–1127. 85 indexed citations

13.

Tsai, Henry, et al.. (2019). Small and Practical BERT Models for Sequence Labeling. 60 indexed citations

14.

Johnson, Melvin, et al.. (2018). Gender-Aware Natural Language Translation. 8 indexed citations

15.

Johnson, Melvin, Mike Schuster, Quoc V. Le, et al.. (2017). Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation. Transactions of the Association for Computational Linguistics. 5. 339–351. 896 indexed citations breakdown →

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact