Noah A. Smith
Impact in
- Artificial Intelligence top 0.01%
- Topic Modeling
- Natural Language Processing Techniques
- Sentiment Analysis and Opinion Mining
- Hate Speech and Cyberbullying Detection
- Domain Adaptation and Few-Shot Learning
- Speech and dialogue systems
- General Social Sciences top 0.02%
Papers in
-
- Natural Language Processing Techniques 191
- Topic Modeling 109
- Sentiment Analysis and Opinion Mining 16
- Machine Learning and Algorithms 8
- Authorship Attribution and Profiling 6
-
- Computational and Text Analysis Methods 19
- Co-authors
- Chris Dyer (41 shared papers)Roy Schwartz (23 shared papers)Yejin Choi (28 shared papers)Swabha Swayamdipta (15 shared papers)Suchin Gururangan (11 shared papers)Bryan Routledge (11 shared papers)Maarten Sap (15 shared papers)Miguel Ballesteros (11 shared papers)
- Journals
- Transactions of the Association for Computational Linguistics (9 papers)Computational Linguistics (7 papers)Journal of Machine Learning Research (3 papers)Synthesis lectures on human language technologies (2 papers)Communications of the ACM (2 papers)
- Partner nations
- United StatesIsraelPortugal
In The Last Decade
Noah A. Smith
303 papers receiving 21.7k citations
Noah A. Smith's Hit Papers
Peers
Comparison fields: 5 of 156
- Artificial Intelligence 17.8k
- General Social Sciences 529
- Safety Research 1k
- Computer Vision and Pattern Recognition 1.5k
- Health Informatics 126
Countries citing papers authored by Noah A. Smith
This map shows the geographic impact of Noah A. Smith'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 Noah A. Smith with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Noah A. Smith more than expected).
Fields of papers citing papers by Noah A. Smith
This network shows the impact of papers produced by Noah A. Smith. 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 Noah A. Smith. The network helps show where Noah A. Smith may publish in the future.
Co-authors
The 25 scholars most cited alongside Noah A. Smith, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 313 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series Hit paper breakdown → | 2010 | 1419 |
| 2 | Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks Hit paper breakdown → | 2020 | 1287 |
| 3 | Green AI Hit paper breakdown → | 2020 | 890 |
| 4 | Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Hit paper breakdown → | 2011 | 785 |
| 5 | Annotation Artifacts in Natural Language Inference Data Hit paper breakdown → | 2018 | 600 |
| 6 | The Risk of Racial Bias in Hate Speech Detection Hit paper breakdown → | 2019 | 546 |
| 7 | ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning Hit paper breakdown → | 2019 | 535 |
| 8 | Retrofitting Word Vectors to Semantic Lexicons Hit paper breakdown → | 2015 | 521 |
| 9 | Knowledge Enhanced Contextual Word Representations Hit paper breakdown → | 2019 | 444 |
| 10 | Transition-Based Dependency Parsing with Stack Long Short-Term Memory Hit paper breakdown → | 2015 | 435 |
| 11 | RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models Hit paper breakdown → | 2020 | 435 |
| 12 | Is Attention Interpretable? Hit paper breakdown → | 2019 | 433 |
| 13 | Linguistic Knowledge and Transferability of Contextual Representations Hit paper breakdown → | 2019 | 420 |
| 14 | A Simple, Fast, and Effective Reparameterization of IBM Model 2 Hit paper breakdown → | 2018 | 404 |
| 15 | Self-Instruct: Aligning Language Models with Self-Generated Instructions Hit paper breakdown → | 2023 | 394 |
| 16 | 2003 | 386 | |
| 17 | Transition-Based Dependency Parsing with Stack Long Short-Term Memory Hit paper breakdown → | 2015 | 348 |
| 18 | Recurrent Neural Network Grammars Hit paper breakdown → | 2016 | 332 |
| 19 | What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA | 2007 | 281 |
| 20 | 2019 | 264 |
About Noah A. Smith
Noah A. Smith is a scholar working on Artificial Intelligence, General Social Sciences, Safety Research, Computer Vision and Pattern Recognition and Statistics, Probability and Uncertainty, having authored 313 papers that have together received 23k indexed citations. Recurring topics across this work include Natural Language Processing Techniques (191 papers), Topic Modeling (109 papers), Computational and Text Analysis Methods (19 papers), Sentiment Analysis and Opinion Mining (16 papers), Machine Learning and Algorithms (8 papers), Ethics and Social Impacts of AI (7 papers), Authorship Attribution and Profiling (6 papers) and Multimodal Machine Learning Applications (6 papers). The work is most often cited by research in Artificial Intelligence (17.8k citations), General Social Sciences (529 citations), Safety Research (1k citations), Computer Vision and Pattern Recognition (1.5k citations) and Health Informatics (126 citations). Noah A. Smith has collaborated with scholars based in United States, Israel and Portugal. Frequent co-authors include Chris Dyer, Roy Schwartz, Yejin Choi, Swabha Swayamdipta, Suchin Gururangan, Bryan Routledge, Maarten Sap, Miguel Ballesteros, Jesse Dodge and Ramnath Balasubramanyan. Their work appears in journals such as Transactions of the Association for Computational Linguistics, Computational Linguistics, Journal of Machine Learning Research, Synthesis lectures on human language technologies and Communications of the ACM.
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.