WordNet: A Lexical Database for English

By George A. Miller. 1995

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. WordNet1 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].

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation (2017, background): “Significant research effort has focused on STS over English sentence pairs.2 English STS is a 1i.a., news headlines, video and image descriptions, glosses from lexical resources including WordNet (Miller, 1995; Fellbaum, 1998), FrameNet (Baker et al., 1998), OntoNotes (Hovy et al., 2006), web discus”
ImageNet Large Scale Visual Recognition Challenge (2014, background): “By us-ing WordNet as a backbone (Miller, 1995), ImageNet already takes care of disambiguating word meanings and of combining together synonyms into the same object category.”
Learning Transferable Visual Models From Natural Language Supervision (2021, background): “Finally all WordNet (Miller, 1995) synsets not already in the query list are added.”
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems (2019, methodology): “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 i”
ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension (2018, background): “…of the sampled queries that required commonsense reasoning, we roughly categorized them into the following four coarse-gained types: Conceptual Knowledge : the presumed knowledge of properties of concepts (Miller, 1995; Liu and Singh, 2004; Pas¸ca and Van Durme, 2008; Zhang et al., 2017).”
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering (2018, methodology): “Unlike the WordNet gain, adding ConceptNet (Speer et al., 2017) introduces a distraction and reduces the score.”
A Simple Method for Commonsense Reasoning (2018, neutral): “0 % USSM + Cause-Effect + WordNet [35] + ConceptNet [36] Knowledge Bases 56.”
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, methodology): “Here we count event as any hyponym of ‘event’ or ‘process’ in WordNet (Miller., 1995).”
Knowledge Enhanced Contextual Word Representations (2019, methodology): “We experiment with integrating both WordNet (Miller, 1995) and Wikipedia, thus explicitly adding word sense knowledge and facts about named entities (including those unseen at training time).”
ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, methodology): “In such cases, we retain the word level alignments from the aligner and perform lexical level entailment assignment with the help of Wordnet and Wikidata.”
Do Image Classifiers Generalize Across Time? (2019, background): “All but one 2 of the object classes in ImageNet-Vid and Youtube-BB are from the WordNet hierarchy [21] and direct ancestors of ILSVRC-2012 classes.”
Do ImageNet Classifiers Generalize to ImageNet? (2019, methodology): “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.”
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018, methodology): “The 1,000 ImageNet class predictions were mapped to the 16 categories using the WordNet hierarchy (Miller, 1995)—e.g. ImageNet category tabby cat would be mapped to cat .”
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016, methodology): “32 × 32 pixels) images that were collected using WordNet (Miller 1995) synsets as queries.”
Webly Supervised Learning of Convolutional Networks (2015, methodology): “After verification the semanticrelatedness with WordNet [31], we add the examples into training dataset.”
Early Convolutions Help Transformers See Better (2021, methodology): “, [35, 40]) that uses WordNet [28] to expand single labels to multiple labels.”