Introduction to WordNet: An On-line Lexical Database

By George A. Miller, R. Beckwith, Christiane D. Fellbaum, Derek Gross, K. Miller. 1990

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

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.”
Reasoning about Quantities in Natural Language (2015, methodology): “To compute the Is-A and synonymy relations we use WordNet (Miller et al., 1990), an ontology of words which contains these relations.”
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints (2017, methodology): “Dataset We evaluate on imSitu (Yatskar et al., 2016) where activity classes are drawn from verbs and roles in FrameNet (Baker et al., 1998) and noun categories are drawn from WordNet (Miller et al., 1990).”
YOLO9000: Better, Faster, Stronger (2016, background): “ImageNet labels are pulled from WordNet, a language database that structures concepts and how they relate [12].”
Generating Visual Explanations (2016, methodology): “METEOR is computed by matching words in generated and reference sentences, but unlike other common metrics such as BLEU [38], uses WordNet [39] to also match synonyms.”
Automatic Acquisition of Hyponyms from Large Text Corpora (1992, methodology): “We use the term hyponym similarly to the sense used in (Miller et al. 1990): a concept represented by a lexical item L0 is said to be a hyponym of the concept represented by a lexical item L1 if native speakers of English accept sentences constructed from the frame An L0 is a (kind of) L1.”
Generation that Exploits Corpus-Based Statistical Knowledge (1998, methodology): “The AMR language is composed of concepts from the SENSUS knowledge base (Knight and Luk, including all of WordNet 1.5 (Miller, 1990), and keywords relating these concepts to each other) An AMR is a labeled directed graph, or feature structure, derived from the PENMAN Sentence Plan Language (Penman,…”
Label Refinery: Improving ImageNet Classification through Label Progression (2018, methodology): “We experiment with using the Wu-Palmer similarity [34] of the WordNet [35] categories to reﬁne the category labels.”
Bootstrapping Path-Based Pronoun Resolution (2006, methodology): “It would be interesting to see whether performance could be improved by adding WordNet and web-mined features.”
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (2016, methodology): “ruth sentences. Among these metrics, BLEU-4 counts the number of matches among the n-grams in generated and reference sentences. METEOR is computed by matching words, but unlike BLEU, it uses WordNet [31] to also match the synonyms. CIDEr counts common n-grams which are TF-IDF weighted which rewards”
BEAT: the Behavior Expression Animation Toolkit (2001, methodology): “The language module currently labels contrasting adjectives by using WordNet to supply information about which words might be synonyms and which might be antonyms to one another [18].”