The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
WordNet: a lexical database for English
Open accessAbstract
Because meaningful sentences are composed of meaningful words, any system that hopes to process natural languages as people do must have information about words and their meanings. This information is traditionally provided through dictionaries, and machine-readable dictionaries are now widely available. But dictionary entries evolved for the convenience of human readers, not for machines. WordNet 1 provides a more effective combination of traditional lexicographic information and modern computing. WordNet is an online lexical database designed for use under program control. English nouns, verbs, adjectives, and adverbs are organized into sets of synonyms, each representing a lexicalized concept. Semantic relations link the synonym sets [4].
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Hierarchical relations are prevalent and indispensable for organizing human knowledge captured by a knowledge graph (KG).”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In fact, knowledge about hierarchical relations (i.e., transitive closure) is explicitly available in the definition of the relation in KGs such as ConceptNet [28], WordNet [8] and Gene Ontology [9].”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [8]
The cited source says what the claim attributes to it.
In the citing paper
“WN18RR is a subset of WordNet [8], which features lexical relationships between word senses.”
From Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (2021) · cites this paper as [8]
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
Introduction to WordNet: An On-line Lexical Database *
Miller, G. A., Beckwith, R., Fellbaum, C., Gross, D., & Miller, K. J. (1990) · International Journal of Lexicography · doi:10.1093/ijl/3.4.235 · Cited by 4,197
Self-citationFREQUENCY ANALYSIS OF ENGLISH USAGE: LEXICON AND GRAMMAR
Francis, W. N., Kučera, H., & Mackie, A. W. (1983) · Medical Entomology and Zoology · Cited by 2,310
Contextual correlates of semantic similarity
Miller, G. A., & Charles, W. G. (1991) · Language and Cognitive Processes · doi:10.1080/01690969108406936 · Cited by 1,634 · cited 1×
“Miller and Charles [ 5 ] proposed that a contextual representation associated with each sense characterizes sentential contexts in which a given word can be used to express that sense.”
BackgroundSelf-citationMiller, G. A., Leacock, C., Tengi, R., & Bunker, R. T. (1993) · DARPA Workshop on Speech and Natural Language (HLT) · doi:10.3115/1075671.1075742 · Cited by 612 · cited 1×
“Semantic concordances are being prepared to provide a basis for empirical studies of sense identification [7].”
BackgroundSelf-citationMiller, G. A., & Fellbaum, C. (1991) · Cognition · doi:10.1016/0010-0277(91)90036-4 · Cited by 452 · cited 1×
“The semantic relations in WordNet [6] were chosen because they apply broadly throughout English and because they are familiar— a user need not have advanced training in linguistics to understand them.”
MethodSelf-citationTowards Building Contextual Representations of Word Senses Using Statistical Models
Leacock, C., Towell, G. G., & Voorhees, E. M. (1993) · Cited by 29
The categorization of sentential contexts
Charles, W. G. (1988) · Journal of Psycholinguistic Research · doi:10.1007/bf01067226 · Cited by 12 · cited 1×
“People are quite skillful in making such distinctions [1].”
Background
Research works printed but not linked: 3
- Francis W. N., 1982, Mass.
- Leacock C., 1993, Proceedings of the Workshop on the Acquisition of Lexical Knowledge from Text, 10
- Miller G. A., 1992, B. Levin and, 197
Cited by
Sorted by citations
Items 1,001–1,047 of 1,047
Contrastive Learning Models for Sentence Representations
Xu, L., Xie, H., Li, Z., Wang, F. L., Wang, W., & Li, Q. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3593590 · Cited by 50
“(Regrouping) antonyms from WordNet [ 72 ], respectively, and then minimizes the N-pair loss [ 96 ] of positive and negative samples and the original text to learn representations.”
BackgroundWiley, J., Hastings, P., Blaum, D., Jaeger, A. J., Hughes, S., Wallace, P., Griffin, T. D., & Britt, M. A. (2017) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-017-0138-z · Cited by 49
“…relations between events using a wide range of linguistic resources and techniques, including part-of-speech tagging, syntactic parsing, WordNet (Miller 1995), VerbOcean for semantic links between verbs (Chklovski and Pantel 2004), dependency parsing, word sense disambiguation (Mihalcea and…”
BackgroundMeasuring text similarity based on structure and word embedding
Farouk, M. (2020) · Cognitive Systems Research · doi:10.1016/j.cogsys.2020.04.002 · Cited by 47
“WordNet (Miller, 1995), which is a lexical database captures human knowledge, is widely used to find similarity between words (Liu and Wang, 2013).”
BackgroundHuber, L. S., Geirhos, R., & Wichmann, F. A. (2023) · Journal of Vision · doi:10.1167/jov.23.7.4 · Cited by 42
“used a mapping from 16 human-friendly entry-level categories to their corresponding ImageNet categories based on the WordNet hierarchy (Miller, 1995).”
MethodNatural Language Processing for Information Extraction
Singh, S. (2018) · arXiv · doi:10.48550/arxiv.1807.02383 · Cited by 45
Commonsense Knowledge Base Completion
Li, X., Taheri, A., Tu, L., & Gimpel, K. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1137 · Cited by 166
Natural language processing in text mining for structural modeling of protein complexes
Badal, V. D., Kundrotas, P. J., & Vakser, I. A. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2079-4 · Cited by 34
“We designated the words “ touch ” and “ site ” as the most semantically similar words relevant to this concept (binding site) to be used in WordNet [44, 45] (generic English lexical database with words grouped into sets of cognitive synonyms), which does not contain any knowledge-domain specific…”
Method“A theme-rewriting approach for generating algebra word problems,”
Koncel-Kedziorski, R., Konstas, I., Zettlemoyer, L., & Hajishirzi, H. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1168 · Cited by 30
Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones
Bai, Y., Ying, R., Ren, H., & Leskovec, J. (2021) · arXiv · doi:10.48550/arxiv.2110.14923 · Cited by 31
“WN18RR is a subset of WordNet [8], which features lexical relationships between word senses.”
BackgroundInfluentialIdentifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease
Chinaei, H., Currie, L. C., Danks, A., Lin, H., Mehta, T., & Rudzicz, F. (2017) · Computational Linguistics · doi:10.1162/coli_a_00290 · Cited by 30
Automatic generation of short answer questions for reading comprehension assessment
HUANG, Y., & HE, L. (2016) · Natural Language Engineering · doi:10.1017/s1351324915000455 · Cited by 30
“As WordNet ranks the senses of a word according to their frequencies in a reference corpus, we set a fixed threshold on the sense numbers to restrict sense frequencies.”
MethodInfluentialThe language of prompting: What linguistic properties make a prompt successful?
Leidinger, A., van Rooij, R., & Shutova, E. (2023) · arXiv · doi:10.48550/arxiv.2311.01967 · Cited by 29
“We quantify word sense ambiguity as the number of word senses in WordNet (Miller, 1995).”
The brain of the beholder: honouring individual representational idiosyncrasies
Charest, I., & Kriegeskorte, N. (2015) · Language, Cognition and Neuroscience · doi:10.1080/23273798.2014.1002505 · Cited by 27
Reliable plagiarism detection system based on deep learning approaches
El-Rashidy, M. A., Mohamed, R. G., El-Fishawy, N. A., & Shouman, M. A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07486-w · Cited by 28
Raković, M., Winne, P. H., Marzouk, Z., & Chang, D. (2021) · Journal of Computer Assisted Learning · doi:10.1111/jcal.12531 · Cited by 26
Formatting biological big data for modern machine learning in drug discovery
Duran‐Frigola, M., Fernández‐Torras, A., Bertoni, M., & Aloy, P. (2019) · WIREs Computational Molecular Science · doi:10.1002/wcms.1408 · Cited by 25
“Inspired by ImageNet 56 and WordNet, 57 MoleculeNet 58 was recently released, containing curated and diverse benchmark collections related to quantum mechanics, physicochemical, bio-physical, and physiological properties of compounds (Figure 1c).”
MethodLiang, C., Yang, X., Wham, D., Pursel, B., Passonneaur, R., & Giles, C. L. (2017) · Proceedings of the Knowledge Capture Conference · doi:10.1145/3148011.3154463 · Cited by 23
“FortheDG problem, many systems utilize WordNet [19] to find synonyms or other related words as distractors [21].”
BackgroundMethodIdeationWeb: Tracking the Evolution of Design Ideas in Human-AI Co-Creation
Shen, H., Shen, L., Wu, W., & Zhang, K. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713375 · Cited by 24
“Early studies predominantly relied on retrieving analogies from pre-collected design knowledge bases [46, 75, 93, 101].”
Talk2Me: Automated linguistic data collection for personal assessment
Komeili, M., Pou-Prom, C., Liaqat, D., Fraser, K. C., Yancheva, M., & Rudzicz, F. (2019) · PLOS ONE · doi:10.1371/journal.pone.0212342 · Cited by 23
“If the word is not found, we use WordNet to check if the category word is its hypernym.”
MethodInfluentialMultimodal Approaches for Alzheimer’s Detection Using Patients’ Speech and Transcript
Cai, H., Huang, X., Liu, Z., Liao, W., Dai, H., Wu, Z., Zhu, D., Ren, H., Li, Q., Liu, T., et al. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-43075-6_34 · Cited by 22
Are Convolutional Neural Networks or Transformers more like human vision?
Tuli, S., Dasgupta, I., Grant, E., & Griffiths, T. L. (2021) · arXiv · doi:10.48550/arxiv.2105.07197 · Cited by 119
“One solution is to cluster the classes into higher-level categories, for example, by using the WordNet hierarchy (Miller, 1995); this gives 16 so-called “entry-level” categories, viz . airplane, bear, bicycle, bird, boat, bottle, car, cat, chair, clock, dog, elephant, keyboard, knife, oven and…”
MethodUsing Natural Language Processing to Predict Item Response Times and Improve Test Construction
Baldwin, P., Yaneva, V., Mee, J., Clauser, B. E., & Ha, L. A. (2021) · Journal of Educational Measurement · doi:10.1111/jedm.12264 · Cited by 20
Prefix Conditioning Unifies Language and Label Supervision
Saito, K., Sohn, K., Zhang, X., Li, C.-L., Lee, C.-Y., Saenko, K., & Pfister, T. (2022) · arXiv · doi:10.48550/arxiv.2206.01125 · Cited by 17
“KLite [34] utilizes external knowledge from WordNet [28] and Wikitionary [27].”
MethodInfluential$360+x$: A Panoptic Multi-modal Scene Understanding Dataset
Chen, H., Hou, Y., Qu, C., Testini, I., Hong, X., & Jiao, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01833 · Cited by 17
“To establish comprehensive and authoritative scene categories that reflect daily life, we referred to the Places Database [34], which is derived from WordNet [18], as our primary basis.”
MethodSelf-supervised Regularization for Text Classification
Zhou, M., Li, Z., & Xie, P. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00389 · Cited by 14
Evolution of Brains and Computers: The Roads Not Taken
Solé, R., & Seoane, L. F. (2022) · Entropy · doi:10.3390/e24050665 · Cited by 14
Context- and subgroup-specific language changes in individuals who develop PTSD after trauma
Todorov, G., Mayilvahanan, K., Cain, C., & Cunha, C. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.00989 · Cited by 13
“For instance, function words, such as pronouns, account for only about 1% of all vocabulary words, but represent approximately 15% of the total words used, and appear to be strongly linked to underlying mental processes (Miller, 1995; Tausczik and Pennebaker, 2010).”
BackgroundTwitchChat: A Dataset for Exploring Livestream Chat
Ringer, C., Nicolaou, M., & Walker, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v16i1.7439 · Cited by 11
Semantic embeddings of generic objects for zero-shot learning
Hascoet, T., Ariki, Y., & Takiguchi, T. (2019) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-018-0371-x · Cited by 9
Quality and Relevance Metrics for Selection of Multimodal Pretraining Data
Rao, R., Rao, S., Nouri, E., Dey, D., Celikyilmaz, A., & Dolan, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00486 · Cited by 6
“These are pruned via WordNet synsets [12] of ImageNet [3] classes, with higher thresholds for ‘relatedness’ creating smaller hashtag sets.”
MethodLi, C., Zhang, R., Wong, J., Gokmen, C., Srivastava, S., Martín-Martín, R., Wang, C., Levine, G., Ai, W., Martinez, B., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.09227 · Cited by 6
“Synsets for object terms and WordNet hierarchy generation: After obtaining an object space for each activity, we take their union and crowdworkers match each one to a WordNet [57] synset.”
BackgroundMethodInfluentialDo Fine-tuned Commonsense Language Models Really Generalize?
Kejriwal, M., & Shen, K. (2020) · arXiv · doi:10.48550/arxiv.2011.09159 · Cited by 6
Establishing trust for using natural language for intent-based networking
Jacobs, A. S., Pfitscher, R. J., Ribeiro, R. H., Granville, L. Z., Ferreira, R. A., Willinger, W., & Rao, S. G. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3574626 · Cited by 5
“Since operators are free to refer to operation targets ( e.g., service, location, or type of traffic) using different words, L UMI relies on WordNet [53] to obtain synonyms of operation targets in both intents and also uses a dictionary of known “handles” for network devices and groups ( i.e.,…”
SAED: Edge-Based Intelligence for Privacy-Preserving Enterprise Search on the Cloud
Zobaed, S. M., Salehi, M. A., & Buyya, R. (2021) · 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid) · doi:10.1109/ccgrid51090.2021.00046 · Cited by 6
Fu, T., Jauw, B., & Sridharan, M. (2025) · 2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/ro-man63969.2025.11217618 · Cited by 3
Box-To-Box Transformations for Modeling Joint Hierarchies
Dasgupta, S. S., Li, X. L., Boratko, M., Zhang, D., & McCallum, A. (2021) · Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021) · doi:10.18653/v1/2021.repl4nlp-1.28 · Cited by 2
(2013) · Cited by 5,726
Microsoft COCO Captions: Data Collection and Evaluation Server
Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., & Zitnick, C. L. (2015) · arXiv · doi:10.48550/arxiv.1504.00325 · Cited by 1,614
“The alignment is based on exact token matching, followed by WordNet synonyms [44], stemmed tokens and then paraphrases.”
MethodSuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019) · arXiv · doi:10.48550/arxiv.1905.00537 · Cited by 1,051
“Systems also may not use the unlabeled test data for the tasks in system development in any way, may not use the structured source data that was used to collect the WiC labels (sense-annotated example sentences from WordNet, VerbNet, and Wiktionary) in any way, and may not build systems that share information across s…”
MethodDo ImageNet Classifiers Generalize to ImageNet?
Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019) · arXiv · doi:10.48550/arxiv.1902.10811 · Cited by 790
“The classes are derived from the WordNet hierarchy [43], which represents each class by a set of synonyms (“synset”) and is organized into semantically meaningful relations.”
BackgroundMethodInfluentialA Simple Method for Commonsense Reasoning
Trinh, T. H., & Le, Q. V. (2018) · arXiv · doi:10.48550/arxiv.1806.02847 · Cited by 293
“0 % USSM + Cause-Effect + WordNet [35] + ConceptNet [36] Knowledge Bases 56.”
Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
Damen, D., Doughty, H., Farinella, G. M., Fidler, S., Furnari, A., Kazakos, E., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2018) · arXiv · doi:10.48550/arxiv.1804.02748 · Cited by 274
“We attempted to automate the clustering of verbs and nouns using combinations of WordNet [32], Word2Vec [31], and Lesk algorithm [4], however, due to limited context there were too many meaningless clusters.”
MethodSimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
Wang, Y., Chao, W.-L., Weinberger, K. Q., & van der Maaten, L. (2019) · arXiv · doi:10.48550/arxiv.1911.04623 · Cited by 245
“The class split is performed using WordNet [20] to ensure that all the base classes are semantically unrelated to the novel classes.”
MethodEvaluation of Text Generation: A Survey
Celikyilmaz, A., Clark, E., & Gao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.14799 · Cited by 207
“In machine translation, Wong & Kit (2019) introduce a feature that can identify lexical cohesion at the sentence level via word-level clustering using WordNet (Miller, 1995) and stemming to obtain a score for each word token, which is averaged over the sentence.”
BackgroundNoise or Signal: The Role of Image Backgrounds in Object Recognition
Xiao, K., Engstrom, L., Ilyas, A., & Madry, A. (2020) · arXiv · doi:10.48550/arxiv.2006.09994 · Cited by 161
“To create it, we group together ImageNet classes sharing an ancestor in the WordNet [Mil95] hierarchy.”
MethodPartial success in closing the gap between human and machine vision
Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2021) · arXiv · doi:10.48550/arxiv.2106.07411 · Cited by 129
“For ImageNet-trained models, in order to obtain a choice from the same 16 categories, the 1,000 class decision vector was mapped to those 16 classes using the WordNet hierarchy [34].”
MethodMulti-relational Poincaré Graph Embeddings
Balažević, I., Allen, C., & Hospedales, T. (2019) · arXiv · doi:10.48550/arxiv.1905.09791 · Cited by 123
“In the WordNet knowledge graph [20], the “hypernym”, “has_part” and “member_meronym” relations each induce different hierarchies over the same set of entities.”
Background
Metadata
- Authors
- Miller, G. A.
- Affiliations
- Princeton University (US)
- Corresponding author
- Miller, George A.
- Venue
- Communications of the ACM
- Published
- 1995-11
- Volume
- 38
- Issue
- 11
- Pages
- 39-41
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2081580037
- Semantic Scholar
- 68c03788224000794d5491ab459be0b2a2c38677
- Cited by
- 14,015
- References
- 7
- Citations by year
- 2026: 335 · 2025: 506 · 2024: 575 · 2023: 721 · 2022: 707 · 2021: 1008 · 2020: 1071 · 2019: 1068 · 2018: 961 · 2017: 841 · 2016: 816 · 2015: 855 · 2014: 723 · 2013: 633 · 2012: 565
- FWCI
- 38.49
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- Funders
- James S. McDonnell Foundation
- Advanced Research Projects Agency
- Office of Naval Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Social Sciences › Arts and Humanities › Language and Linguistics › Lexicography and Language Studies
- Physical Sciences › Computer Science › Artificial Intelligence › Semantic Web and Ontologies
- Keywords
- WordNet, lexical databases, synonym sets, semantic relations, word meaning, natural language processing, machine-readable dictionaries, English vocabulary
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
