Natural Language Processing

Core language tasks and representations not covered by a more specific NLP subfield.

A topic in the Science corpus, drawn from 6,833 papers.

Trusted voices in Natural Language Processing

Ordered by the trust Natural Language Processing's own network concentrates on each researcher, most first.

  1. Christopher D. Manning — trusted by 7,585 researchers here
  2. Yoshua Bengio — trusted by 6,511 researchers here
  3. Richard Socher — trusted by 5,322 researchers here
  4. Kyunghyun Cho — trusted by 5,285 researchers here
  5. Quoc V. Le — trusted by 4,661 researchers here
  6. Tomas Mikolov — trusted by 4,572 researchers here
  7. Ilya Sutskever — trusted by 4,531 researchers here
  8. Jason Aaron Edward Weston — trusted by 4,102 researchers here
  9. Dzmitry Bahdanau — trusted by 4,340 researchers here
  10. Oriol Vinyals — trusted by 4,039 researchers here
  11. Kenton C. T. Lee — trusted by 4,160 researchers here
  12. Percy Liang — trusted by 3,794 researchers here

Most-cited papers in Natural Language Processing

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Attention is All you Need (2017, Neural Information Processing Systems) — 185,508 citations
  2. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019, North American Chapter of the Association for Computational Linguistics) — 118,136 citations
  3. Distributed Representations of Words and Phrases and their Compositionality (2013, Neural Information Processing Systems) — 35,459 citations
  4. GloVe: Global Vectors for Word Representation (2014) — 34,790 citations
  5. Efficient Estimation of Word Representations in Vector Space (2013) — 34,723 citations
  6. Bleu: a Method for Automatic Evaluation of Machine Translation (2002) — 33,928 citations
  7. RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019, arXiv.org) — 30,530 citations
  8. Neural Machine Translation by Jointly Learning to Align and Translate (2014, International Conference on Learning Representations) — 29,733 citations
  9. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation (2014) — 26,848 citations
  10. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019, Journal of machine learning research) — 26,606 citations
  11. Sequence to Sequence Learning with Neural Networks (2014, Neural Information Processing Systems) — 22,211 citations
  12. ROUGE: A Package for Automatic Evaluation of Summaries (2004) — 21,161 citations
  13. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019) — 19,155 citations
  14. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data (2001) — 15,607 citations
  15. Convolutional Neural Networks for Sentence Classification (2014) — 14,347 citations
  16. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (2019) — 13,006 citations
  17. Deep Contextualized Word Representations (2018, North American Chapter of the Association for Computational Linguistics) — 12,212 citations
  18. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (2015) — 10,867 citations
  19. Enriching Word Vectors with Subword Information (2016) — 10,838 citations
  20. Distributed Representations of Sentences and Documents (2014) — 9,778 citations
  21. Thumbs up? Sentiment Classification using Machine Learning Techniques (2002) — 9,588 citations
  22. SQuAD: 100,000+ Questions for Machine Comprehension of Text (2016) — 9,586 citations
  23. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013) — 9,576 citations
  24. XLNet: Generalized Autoregressive Pretraining for Language Understanding (2019, Neural Information Processing Systems) — 9,461 citations
  25. google,我,萨娜 (2006) — 9,238 citations
  26. BERTScore: Evaluating Text Generation with BERT (2019) — 9,100 citations
  27. Machine learning in automated text categorization (2001) — 9,090 citations
  28. Speech recognition with deep recurrent neural networks (2013) — 9,035 citations
  29. Neural Machine Translation of Rare Words with Subword Units (2015) — 8,868 citations
  30. Unsupervised Cross-lingual Representation Learning at Scale (2019) — 8,807 citations
  31. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (2018) — 8,768 citations
  32. Mining and summarizing customer reviews (2004) — 8,541 citations
  33. Effective Approaches to Attention-based Neural Machine Translation (2015) — 8,424 citations
  34. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments (2005) — 8,297 citations
  35. Axiomatic Attribution for Deep Networks (2017) — 8,293 citations
  36. Natural Language Processing (Almost) from Scratch (2011) — 7,931 citations
  37. A Neural Probabilistic Language Model (2003) — 7,861 citations
  38. The Stanford CoreNLP Natural Language Processing Toolkit (2014) — 7,642 citations
  39. BioBERT: a pre-trained biomedical language representation model for biomedical text mining (2019) — 7,641 citations
  40. On the Properties of Neural Machine Translation: Encoder–Decoder Approaches (2014) — 7,554 citations
  41. The spread of true and false news online (2018) — 7,469 citations
  42. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016) — 7,325 citations
  43. Character-level Convolutional Networks for Text Classification (2015) — 7,191 citations
  44. Parameter-Efficient Transfer Learning for NLP (2019) — 6,877 citations
  45. Finding scientific topics (2004) — 6,704 citations
  46. Probabilistic topic models (2012) — 6,644 citations
  47. Show and tell: A neural image caption generator (2014) — 6,597 citations
  48. Moses: Open Source Toolkit for Statistical Machine Translation (2007) — 6,539 citations
  49. Protein data bank (2012) — 6,228 citations
  50. Foundations of Statistical Natural Language Processing (2001) — 6,195 citations

Most active researchers

By papers in this topic: a volume measure, not trust.