Ultradense Word Embeddings by Orthogonal Transformation
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Embeddings are generic representations that are useful for many NLP tasks. In this paper, we introduce DENSIFIER, a method that learns an orthogonal transformation of the embedding space that focuses the information relevant for a task in an ultradense subspace of a dimensionality that is smaller by a factor of 100 than the original space. We show that ultradense embeddings generated by DENSIFIER reach state of the art on a lexicon creation task in which words are annotated with three types of lexical information - sentiment, concreteness and frequency. On the SemEval2015 10B sentiment analysis task we show that no information is lost when the ultradense subspace is used, but training is an order of magnitude more efficient due to the compactness of the ultradense space.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Mining and summarizing customer reviews
Hu, M., & Liu, B. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014073 · Cited by 7,793
A Convolutional Neural Network for Modelling Sentences
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1062 · Cited by 3,601
Kiros, R., Zhu, Y., Salakhutdinov, R., Zemel, R. S., Torralba, A., Urtasun, R., & Fidler, S. (2015) · arXiv · doi:10.48550/arxiv.1506.06726 · Cited by 1,293
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
Tang, D., Wei, F., Yang, N., Zhou, M., Liu, T., & Qin, B. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1146 · Cited by 1,181
Cited by
SemEval-2018 Task 1: Affect in Tweets
Mohammad, S., Bravo-Marquez, F., Salameh, M., & Kiritchenko, S. (2018) · Proceedings of The 12th International Workshop on Semantic Evaluation · doi:10.18653/v1/s18-1001 · Cited by 746
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora
Hamilton, W. L., Clark, K., Leskovec, J., & Jurafsky, D. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1057 · Cited by 355
Techno-Economic Assessment of Three Modes of Large-Scale Crop Residue Utilization Projects in China
Meng, L., Alengebawy, A., Ai, P., Jin, K., Chen, M., & Pan, Y. (2020) · Energies · doi:10.3390/en13143729 · Cited by 31
A Computational Analysis of Polarization on Indian and Pakistani Social Media
Tyagi, A., Field, A., Lathwal, P., Tsvetkov, Y., & Carley, K. M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-60975-7_27 · Cited by 20
Metadata
- Authors
- Rothe, S., Ebert, S., & Schütze, H.
- Venue
- Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Published
- 2016
- Pages
- 767-777
- OpenAlex
- W2286496058
- Cited by
- 116
- References
- 4
- FWCI
- 11.62
- Type
- conference paper
- Language
- en
- Open access
- green
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: Ultradense Word Embeddings by Orthogonal Transformation. https://app.cochat.ai/papers/10.18653/v1/n16-1091
- The paper
- Rothe, S., Ebert, S., & Schütze, H. (2016). Ultradense Word Embeddings by Orthogonal Transformation. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. https://doi.org/10.18653/v1/n16-1091
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.