The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Open accessAbstract
Preface by the Program Committee Co-ChairsWelcome to EMNLP 2020!Due to the unprecedented situation with the Covid-19 pandemic, EMNLP 2020 will be held completely online this year.We decided to move EMNLP to a virtual format early on, when the pandemic just started, and postponed the paper submission deadlines by three weeks such that authors affected by the pandemic could have more time for their paper submissions.This resulted in a much tighter schedule for paper review and decisions, as well as publications, workshop programs, virtual infrastructure, etc.However, thanks to everyone's hard work, we made it.We received a record number of 3,677 submissions.This is a significant increase of 26% over EMNLP 2019, making it the largest NLP conference to date in terms of paper submissions.After removing withdrawals and desk rejecting papers which violated our formatting requirements, the anonymity policy, or double submission policy, 3,359 submissions were sent out for review.Despite the sharp increase in submissions, we kept the acceptance rates at a similar level as past years.The acceptance statistics are shown below: Long Short Total Reviewed 2,455 904 3,359 Accepted 602 150 752 Acceptance Rate 24.6% 16.6% 22.4% It is important to have a well-organized review structure to handle a large number of submissions.We first set up a total of 21 tracks (including a special Multidisciplinary and Area Chair Conflict of Interest track) based on the track information in past conferences such as ACL 2020, EMNLP 2019 and NAACL 2019.We used the submission numbers per track from past conferences to estimate the number of Senior Area Chairs (SACs) and Area Chairs (ACs) required for each track.We eventually recruited 33 SACs and 196 ACs.For reviewer recruitment, we started with the reviewer lists from NAACL 2019, EMNLP 2019 and ACL 2020 and sent out initial invitations asking reviewers to express their track preferences.In addition, we introduced a new policy that in order to submit paper(s) to EMNLP, at least one author must be nominated to serve as a reviewer (usually the most senior author) and for that author to take on a full load of up to 6 reviews.We filtered out some reviewers who were less experienced in paper review or did not hold a PhD degree (except those final-year PhD students).We then passed the reviewer list to SACs and asked them to select from these candidate reviewers based on their expertise and semantic scholar profiles.Overall, this resulted in a total of 2,633 reviewers.For AC assignments, we matched papers with ACs automatically based on comparing submissions' abstracts with ACs' past papers in ACL* venues, using semantic scholar to harvest this data.For reviewer assignment, we generated a "seniority score" for each reviewer based on their past publication record and recent ACL* papers.Where possible, we have ensured every paper has at least one "senior" reviewer and not more than one "junior" reviewer.As a result of ever increasing paper submissions, review quality is a pressing issue in our community.To help improve review quality, this year we prepared review guidelines with explicit dos and don'ts.We observed many cases where authors called out problems in reviews for these papers based on these guidelines, ACs took action, and reviewers revised their reviews.Overall the review guidelines seem to be well received by authors and reviewers, and we feel they lead to improved reviews in aggregate.Having said this, we emphasize that the guidelines are only a partial solution, and more work is needed vii from the entire community to manage the increasing submissions and continue to maintain or improve review quality.Authors resubmitting papers that were previously rejected from another publication venue were given the option of providing these previous reviews and a rejoinder as part of their submission.This was designed to accommodate authors who have improved their paper based on previous feedback, and feel they have addressed the key issues raised, and would benefit from having this considered as part of the EMNLP review process.Roughly, this is designed to mimic the "revise-and-resubmit" procedure in a journal.These "sticky reviews" were made available to the AC, SACs and PCs, but not the reviewers, lest it bias their assessments.A total of 349 submissions used this facility.While we do not have firm numbers confirming the utility of sticky reviews, we feel that it was useful for making decisions for borderline submissions, where the past reviews and quality of the rejoinder could be used to justify paper acceptance.This year we experimented with "Findings", a new publication model based on an idea floated in the ACL reviewing committee, designed to allow more papers to be accepted for publication beyond those accepted to the main conference.Please see the Preface to the Findings of ACL: EMNLP 2020 for a detailed description of this new initiative, including the acceptance rate and processes specific
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Generating Radiology Reports via Memory-driven Transformer
Chen, Z., Song, Y., Chang, T.-H., & Wan, X. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.112 · Cited by 693
BAE: BERT-based Adversarial Examples for Text Classification
Garg, S., & Ramakrishnan, G. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.498 · Cited by 478
Event Extraction as Machine Reading Comprehension
Liu, J., Chen, Y., Liu, K., Bi, W., & Liu, X. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.128 · Cited by 303
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
Wang, J., & Lu, W. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.133 · Cited by 216
SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge
Ke, P., Ji, H., Liu, S., Zhu, X., & Huang, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.567 · Cited by 191
Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!
Sia, S., Dalmia, A., & Mielke, S. J. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.135 · Cited by 186
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
Zhao, X., Wu, W., Xu, C., Tao, C., Zhao, D., & Yan, R. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.272 · Cited by 185
Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
Chen, S., Hou, Y., Cui, Y., Che, W., Liu, T., & Yu, X. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.634 · Cited by 163
Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
Sheng, J., Guo, S., Chen, Z.-Y., Yue, J., Wang, L., Liu, T., & Xü, H. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.131 · Cited by 152
Efficient One-Pass End-to-End Entity Linking for Questions
Li, B. Z., Min, S., Iyer, S. V., Mehdad, Y., & Yih, W.-T. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.522 · Cited by 140
Cited by
Sentiment Analysis and Opinion Mining
Zhang, L., & Liu, B. (2017) · Encyclopedia of Machine Learning and Data Mining · doi:10.1007/978-1-4899-7687-1_907 · Cited by 3,260
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688
Word sense disambiguation: A survey
Navigli, R. (2009) · ACM Computing Surveys · doi:10.1145/1459352.1459355 · Cited by 1,819
Annotating Expressions of Opinions and Emotions in Language
Wiebe, J., Wilson, T., & Cardie, C. (2005) · Language Resources and Evaluation · doi:10.1007/s10579-005-7880-9 · Cited by 1,755
Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach
Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Dziurzynski, L., Ramones, S. M., Agrawal, M., Shah, A., Kosinski, M., Stillwell, D., Seligman, M. E. P., et al. (2013) · PLoS ONE · doi:10.1371/journal.pone.0073791 · Cited by 1,700
Metadata
- Published
- 2020
- OpenAlex
- W2489487449
- Cited by
- 1,282
- References
- 63
- Type
- paratext
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://app.cochat.ai/papers/10.18653/v1/2020.emnlp-main
- The paper
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). (2020). https://doi.org/10.18653/v1/2020.emnlp-main
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.