An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification
Open accessAbstract
This paper explores an unsupervised approach to learning a compositional representation function for multi-word expressions (MWEs), and evaluates it on the Tratz dataset, which associates two-word expressions with the semantic relation between the compound constituents (e.g. the label employer is associated with the noun compound government agency) (Tratz, 2011).The composition function is based on recurrent neural networks, and is trained using the Skip-Gram objective to predict the words in the context of MWEs.Thus our approach can naturally leverage large unlabeled text sources.Further, our method can make use of provided MWEs when available, but can also function as a completely unsupervised algorithm, using MWE boundaries predicted by a single, domain-agnostic part-of-speech pattern.With pre-defined MWE boundaries, our method outperforms the previous state-of-the-art performance on the coarse-grained evaluation of the Tratz dataset (Tratz, 2011), with an F1 score of 50.4%.The unsupervised version of our method approaches the performance of the supervised one, and even outperforms it in some configurations.
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
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Zhang et al. proposed a non-intrusive appliance state detection system that uses a single sensor to monitor multiple appliances via a cloud-edge-device collaborative framework.
“Zhang et al. proposed a non-intrusive appliance state detection system [235] that uses a single sensor to monitor multiple appliances via a cloud-edgedevice collaborative framework.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [235]
The Abstract and Introduction describe a method for learning representations of multi-word expressions, not an appliance-monitoring system. Searches for non-intrusive appliance detection, a single sensor, and a cloud-edge-device framework found no passage addressing the claim. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · see citing works
Jakubův, J., Chvalovský, K., Goertzel, Z., et al. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,648 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · see citing works
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · see citing works
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · see citing works
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · see citing works
Human behavior and the principle of least effort
Zipf, G. K. (1949) · Max Planck Digital Library · Cited by 6,598 · see citing works
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100 · see citing works
Automatic acquisition of hyponyms from large text corpora
Hearst, M. A. (1992) · International Conference on Computational Linguistics · doi:10.3115/992133.992154 · Cited by 3,302 · see citing works
Human behavior and the principle of least effort.
indicated, N. A. (1949) · Journal of Consulting Psychology · doi:10.1037/h0052803 · Cited by 1,587 · see citing works
Mathematical structures of language
Harris, Z. S. (1968) · Medical Entomology and Zoology · Cited by 957 · see citing works
Composition in Distributional Models of Semantics
Mitchell, J., & Lapata, M. (2010) · Cognitive Science · doi:10.1111/j.1551-6709.2010.01106.x · Cited by 946 · see citing works
Regularizing and Optimizing LSTM Language Models
Merity, S., Keskar, N. S., & Socher, R. (2017) · arXiv · doi:10.48550/arxiv.1708.02182 · Cited by 697 · see citing works
Wieting, J., & Gimpel, K. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-1042 · Cited by 318 · see citing works
Do Supervised Distributional Methods Really Learn Lexical Inference Relations?
Levy, O., Remus, S., Biemann, C., & Dagan, I. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1098 · Cited by 211 · see citing works
Neural Models for Key Phrase Extraction and Question Generation
Subramanian, S., Wang, T., Yuan, X., Zhang, S., Trischler, A., & Bengio, Y. (2018) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/w18-2609 · Cited by 97 · see citing works
A Taxonomy, Dataset, and Classifier for Automatic Noun Compound Interpretation
Tratz, S., & Hovy, E. H. (2010) · Cited by 95 · see citing works
Learning Composition Models for Phrase Embeddings
Yu, M., & Dredze, M. H. (2015) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00135 · Cited by 79 · see citing works
SemEval-2013 Task 4: Free Paraphrases of Noun CompoundsPreprint
Hendrickx, I., Nakov, P., Śzpakowicz, S., Kozareva, Z., Séaghdha, D. Ó., & Veale, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.10421 · Cited by 51 · see citing works
SemEval-2 Task 9: The Interpretation of Noun Compounds Using Paraphrasing Verbs and Prepositions
Butnariu, C., Kim, S. N., Nakov, P., Séaghdha, D. Ó., Śzpakowicz, S., & Veale, T. (2010) · Cited by 39 · see citing works
Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations
Shwartz, V., & Dagan, I. (2018) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.18653/v1/p18-1111 · Cited by 22 · see citing works
Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext
Wieting, J., Mallinson, J., & Gimpel, K. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1026 · Cited by 21 · see citing works
Semantically-enriched parsing for natural language understanding
Tratz, S. (2015) · University of Southern California Digital Library · doi:10.25549/usctheses-c3-176191 · Cited by 20 · see citing works
Shwartz, V., & Waterson, C. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-2035 · Cited by 20 · see citing works
Multi-word expression identification using sentence surface features
Boukobza, R., & Rappoport, A. (2009) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/1699571.1699573 · Cited by 19 · see citing works
On the Compositionality and Semantic Interpretation of English Noun Compounds
Dima, C. (2016) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w16-1604 · Cited by 17 · see citing works
Shwartz, V., & Waterson, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08073 · Cited by 10 · see citing works
A Systematic Comparison of English Noun Compound Representations
Shwartz, V. (2019) · Workshop on Multiword Expressions (MWE) · doi:10.18653/v1/w19-5111 · Cited by 7 · see citing works
Information Retrieval System Using Multiwords Expressions (MWE) as Descriptors
da Silva, E. M., & Souza, R. R. (2012) · Journal of Information Systems and Technology Management · doi:10.4301/s1807-17752012000200002 · Cited by 5 · see citing works
Paraphrase to Explicate: Revealing Implicit Noun-Compound RelationsPreprint
Shwartz, V., & Dagan, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.02442 · Cited by 5 · see citing works
Multiword expressions in multilingual information extraction
Thurmair, G. (2018) · Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory · doi:10.1075/cilt.341.05thu · Cited by 2 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
Cited by
Sorted by citations
Multimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“Researchers are also investigating how to integrate context-aware modeling with techniques like reinforcement learning [236] and unsupervised learning to create smarter and more adaptive decision-making processes [237].”
Dao, A., Kertkeidkachorn, N., & Ichise, R. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.08.133 · Cited by 4 · see citing works
A Generic Tool for Identification of Indo-Aryan Multi Word Expression
Saini, J. R., & Gaikwad, H. (2023) · SN Computer Science · doi:10.1007/s42979-023-02181-6 · Cited by 3 · see citing works
Identification of Multi-word Expressions Using Language-Specific Composite Master Lists
Gaikwad, H., & Saini, J. R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8526-1_4
Gaikwad, H., & Saini, J. R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8043-6_1
- Authors
- Vacareanu, R., Valenzuela-Escárcega, M. A., Sharp, R., & Surdeanu, M.
- Affiliations
- University of Arizona (US)
- ORCID
- Surdeanu, Mihai
- Venue
- Proceedings of the 28th International Conference on Computational Linguistics
- Published
- 2020
- Pages
- 3346-3356
- ISSN
- 1525-2477 (ISSN-L)
- OpenAlex
- W3115512991
- Cited by
- 5
- References
- 34
- Citations by year
- 2025: 3 · 2023: 1 · 2021: 1
- FWCI
- 0.19
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- International Conference on Computational Linguistics (publishedVersion, cc-by)
- Funders
- National Science Foundation (2006583)
- University of Arizona
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- multiword expressions, semantic relation classification, recurrent neural networks, skip-gram, unsupervised learning
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
