Danqi Chen

Research output

Research output per year 2011 2020 2021 2022 2023

• 27 Conference contribution
• 8 Paper
• 2 Article
• 2 Conference article
• 2 More
  • 2 Editorial

Research output per year

Research output per year

Search results

• 2023

  Should You Mask 15% in Masked Language Modeling?

  Wettig, A., Gao, T., Zhong, Z. & Chen, D., 2023, EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 2977-2992 16 p. (EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Language Modeling 100%
  • Masking 74%
  • Mask 68%
  • Masks 50%
  • Language Model 18%

• SIGIR 2023 Workshop on Retrieval Enhanced Machine Learning (REML @ SIGIR 2023)

  Bendersky, M., Diaz, F., Chen, D. & Zamani, H., Jul 19 2023, SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, p. 3468-3471 4 p. (SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Machine learning 100%
  • Electric grounding 16%
  • Information retrieval 14%
  • Data storage equipment 9%
  • Industry 6%
• 2022

  Can Rationalization Improve Robustness?

  Chen, H., He, J., Narasimhan, K. & Chen, D., 2022, NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 3792-3805 14 p. (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Natural language processing systems 100%
  • Set theory 52%
  • Experiments 29%
  6 Scopus citations

• Ditch the Gold Standard: Re-evaluating Conversational Question Answering

  Li, H., Gao, T., Goenka, M. & Chen, D., 2022, ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Muresan, S., Nakov, P. & Villavicencio, A. (eds.). Association for Computational Linguistics (ACL), p. 8074-8085 12 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics; vol. 1).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Gold Standard 100%
  • Ditch 97%
  • gold standard 94%
  • Question Answering 89%
  • conversation 58%
  5 Scopus citations

• Recovering Private Text in Federated Learning of Language Models

  Gupta, S., Huang, Y., Zhong, Z., Gao, T., Li, K. & Chen, D., 2022, Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022. Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K. & Oh, A. (eds.). Neural information processing systems foundation, (Advances in Neural Information Processing Systems; vol. 35).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Gradient methods 100%
  • Recovery 55%

• Structured Pruning Learns Compact and Accurate Models

  Xia, M., Zhong, Z. & Chen, D., 2022, ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Muresan, S., Nakov, P. & Villavicencio, A. (eds.). Association for Computational Linguistics (ACL), p. 1513-1528 16 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics; vol. 1).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Distillation 100%
  • Train 36%
  • Language Model 26%
  • Granularity 26%
  • Latency 21%
  10 Scopus citations
• 2021

  A Frustratingly Easy Approach for Entity and Relation Extraction

  Zhong, Z. & Chen, D., 2021, NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 50-61 12 p. (NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Multi-task learning 100%
  • Casting 63%
  147 Scopus citations

• Factual Probing Is [MASK]: Learning vs. Learning to Recall

  Zhong, Z., Friedman, D. & Chen, D., 2021, NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 5017-5033 17 p. (NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Set theory 100%
  • Experiments 55%
  83 Scopus citations

• Learning dense representations of phrases at scale

  Lee, J., Sung, M., Kang, J. & Chen, D., 2021, ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 6634-6647 14 p. (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Learning 100%
  • Retrieval 83%
  • Transfer Learning 41%
  • learning 37%
  • Inference 36%
  35 Scopus citations

• Making pre-trained language models better few-shot learners

  Gao, T., Fisch, A. & Chen, D., 2021, ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 3816-3830 15 p. (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Language Model 100%
  • Tuning 74%
  • Prompts 37%
  • Resources 23%
  • Learning 22%
  323 Scopus citations

• Non-Parametric Few-Shot Learning for Word Sense Disambiguation

  Chen, H., Xia, M. & Chen, D., 2021, NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 1774-1781 8 p. (NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
  4 Scopus citations

• Phrase Retrieval Learns Passage Retrieval, Too

  Lee, J., Wettig, A. & Chen, D., 2021, EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), p. 3661-3672 12 p. (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Retrieval 100%
  • Natural language processing systems 96%
  • Vector quantization 88%
  • Document Retrieval 12%
  • Vector Quantization 11%
  13 Scopus citations

• SimCSE: Simple Contrastive Learning of Sentence Embeddings

  Gao, T., Yao, X. & Chen, D., 2021, EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), p. 6894-6910 17 p. (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Learning 100%
  • Drop out 72%
  • Semantic Similarity 53%
  • Semantics 37%
  • Data Augmentation 36%
  492 Scopus citations

• Simple Entity-Centric Questions Challenge Dense Retrievers

  Sciavolino, C., Zhong, Z., Lee, J. & Chen, D., 2021, EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), p. 6138-6148 11 p. (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Encoder 100%
  • Retrieval 94%
  • Training 79%
  • Question Answering 53%
  • Data Augmentation 50%
  18 Scopus citations

• Single-dataset Experts for Multi-dataset Question Answering

  Friedman, D., Dodge, B. & Chen, D., 2021, EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), p. 6128-6137 10 p. (EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Question Answering 100%
  • Training 74%
  • Multi-model 26%
  • Overfitting 23%
  • Transformer 23%
  6 Scopus citations
• 2020

  Dense passage retrieval for open-domain question answering

  Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D. & Yih, W. T., 2020, EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 6769-6781 13 p. (EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Question Answering 100%
  • Retrieval 88%
  • Vector spaces 72%
  • TF-IDF 46%
  • Vector Space Model 42%
  650 Scopus citations

• Open-domain question answering

  Chen, D. & Yih, W. T., 2020, ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Tutorial Abstracts. Association for Computational Linguistics (ACL), p. 34-37 4 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Question Answering 100%
  35 Scopus citations

• TextHide: Tackling data privacy in language understanding tasks

  Huang, Y., Song, Z., Chen, D., Li, K. & Arora, S., 2020, Findings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020. Association for Computational Linguistics (ACL), p. 1368-1382 15 p. (Findings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Privacy 100%
  • Encryption 91%
  • Data privacy 80%
  • Cryptography 64%
  • Language Model 62%
  18 Scopus citations
• 2019

  A discrete hard EM approach for weakly supervised question answering

  Min, S., Chen, D., Hajishirzi, H. & Zettlemoyer, L., 2019, EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics, p. 2851-2864 14 p. (EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Question Answering 100%
  • Update 34%
  • Learning 31%
  • Marginal Likelihood 22%
  • Discrete Variables 21%
  81 Scopus citations

• Mrqa 2019 shared task: Evaluating generalization in reading comprehension

  Fisch, A., Talmor, A., Jia, R., Seo, M., Choi, E. & Chen, D., 2019, MRQA@EMNLP 2019 - Proceedings of the 2nd Workshop on Machine Reading for Question Answering. Association for Computational Linguistics (ACL), p. 1-13 13 p. (MRQA@EMNLP 2019 - Proceedings of the 2nd Workshop on Machine Reading for Question Answering).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Multi-task learning 100%
  • Sampling 52%
  128 Scopus citations
• 2017

  Position-aware attention and supervised data improve slot filling

  Zhang, Y., Zhong, V., Chen, D., Angeli, G. & Manning, C. D., 2017, EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), p. 35-45 11 p. (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  • Knowledge 100%
  • Crowdsourcing 96%
  • Model 85%
  • Knowledge Base 85%
  • Form 53%
  473 Scopus citations

• Reading Wikipedia to answer open-domain questions

  Chen, D., Fisch, A., Weston, J. & Bordes, A., 2017, ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), p. 1870-1879 10 p. (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); vol. 1).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  • Wikipedia 100%
  • Multi-task learning 49%
  • Recurrent neural networks 38%
  • Neural Network Model 37%
  • neural network 29%
  794 Scopus citations
• 2016

  A thorough examination of the CNN/daily mail reading comprehension task

  Chen, D., Bolton, J. & Manning, C. D., 2016, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), p. 2358-2367 10 p. (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; vol. 4).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  • CNN 100%
  • Reading Comprehension 97%
  • Daily Mail 57%
  • comprehension 54%
  • News Articles 53%
  297 Scopus citations
• 2015

  Representing text for joint embedding of text and knowledge bases

  Toutanova, K., Chen, D., Pantel, P., Poon, H., Choudhury, P. & Gamon, M., 2015, Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), p. 1499-1509 11 p. (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  • Knowledge Base 100%
  • Text 71%
  • Model 20%
  • Substructure 17%
  • Optimise 16%
  451 Scopus citations
• 2014

  A fast and accurate dependency parser using neural networks

  Chen, D. & Manning, C. D., 2014, EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 740-750 11 p. (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  Open Access

  • Classifier 100%
  • Neural Networks 83%
  • Classifiers 62%
  • Parsing 60%
  • Neural networks 53%
  1301 Scopus citations
• 2012

  Beyond ten blue links: Enabling user click modeling in federated Web search

  Chen, D., Chen, W., Wang, H., Chen, Z. & Yang, Q., 2012, WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, p. 463-472 10 p. (WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Search engines 100%
  • HTML 39%
  49 Scopus citations
• 2011

  Characterizing inverse time dependency in multi-class learning

  Chen, D., Chen, W. & Yang, Q., 2011, Proceedings - 11th IEEE International Conference on Data Mining, ICDM 2011. Institute of Electrical and Electronics Engineers Inc., p. 1020-1025 6 p. 6137308. (Proceedings - IEEE International Conference on Data Mining, ICDM).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

  • Learning algorithms 100%
  • Experiments 42%
  2 Scopus citations