Book Reviews: WordNet: An Electronic Lexical Database

By Dekang Lin. 1999

Subfields: Natural Language Processing, Computational Linguistics & Semantics

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

In Computational Linguistics & Semantics

Citations in the corpus

Microsoft COCO: Common Objects in Context (2014, methodology): “Unlike previous datasets containing entry-level categories [29], such as “dog” or “chair,” like [28], ImageNet used the WordNet Hierarchy [30] to obtain both entry-level and ﬁne-grained [31] categories.”
What makes ImageNet good for transfer learning? (2016, methodology): “The 1000 classes of the ImageNet challenge [37] are derived from leaves of the WordNet tree [15].”
“I’m sorry to hear that”: Finding New Biases in Language Models with a Holistic Descriptor Dataset (2022, background): “2017), as well as WordNet synonyms and antonyms (Fellbaum and Miller, 1998).”
oLMpics-On What Language Model Pre-training Captures (2019, methodology): “, 2017) and WORDNET (Fellbaum, 1998), and use Google Books Corpus to choose pairs that occur frequently in language.”
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, methodology): “This results in a similarity metric that has better coverage on our data set than WordNet based metrics, and is much more specific than distributional similarities which capture broad topical relatedness rather than semantic equivalence.”
SUN database: Large-scale scene recognition from abbey to zoo (2010, positive): “However, we use this to validate the completeness of the list provided by WordNet.”
LVIS: A Dataset for Large Vocabulary Instance Segmentation (2019, methodology): “Speciﬁcally, in LVIS each category c is a WordNet synset —a word sense speciﬁed by a set of synonyms and a deﬁnition.”
Unsupervised Learning from Narrated Instruction Videos (2015, methodology): “We use a negative cost when d1 and d2 are similar according to the distance in the WordNet tree [11, 21] of their verb and direct object constituents, and positive if they are dissimilar (details are given in Sec.”
SIGMa: simple greedy matching for aligning large knowledge bases (2012, methodology): “ASES 2.1 Motivating example: YAGO and IMDb Consider merging the information in the following two knowledge bases: 1. YAGO, a large semantic knowledge base derived from English Wikipedia [27], WordNet [9] and GeoNames.3 2. IMDb, a large popular online database that stores information about movies.4 T”
Tailor: Generating and Perturbing Text with Semantic Controls (2021, methodology): “5 For example, if combined with WordNet (Miller, 1998), T ailor perturbations may be able to incorporate a subset of natural logic (MacCartney and Manning, 2014): In Figure 1, we can create an entailment relationship by replacing doctor with its hyponym adult.”
Adversarial Examples for Evaluating Reading Comprehension Systems (2017, methodology): “We replace nouns and adjectives with antonyms from WordNet (Fellbaum, 1998), and change named entities and numbers to the nearest word in GloVe word vector space 2 (Pennington et al., 2014) with the same part of speech.”
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, methodology): “Beyond that, external knowledge is collected for each dataset to further augment language, including WordNet hierarchy [42], WordNet definition [42], Wiktionary definition [41], and GPT-3 knowledge [4], which represents the first comprehensive benchmark in evaluating large-scale task-level transfer.”
Towards fairer datasets: filtering and balancing the distribution of the people subtree in the ImageNet hierarchy (2019, background): “WordNet [53] emerges as a natural answer.”
Learning Gender-Neutral Word Embeddings (2018, methodology): “We categorize all the vocabulary words into three subsets: male-definition ΩM , female-definition ΩF , and gender-neutral ΩN , based on their definition in WordNet (Miller and Fellbaum, 1998).”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Automatic thesaurus generation: WordNet is a popular tool for research in natural language processing (Fellbaum, 1998), but creating and maintaing such lexical resources 30.”
Exploring Models and Data for Image Question Answering (2015, background): “In this work we consider the following two simple constraints: (1) Aover-A principle which restricts the movement of a whword inside a noun phrase (NP) (Chomsky, 1973); (2) Our algorithm does not move any wh-word that is contained in a clause constituent.”
A dataset for Movie Description (2015, methodology): “VerbNet is already mapped to WordNet, thus we map to VerbNet via WordNet.”
SemEval-2014 Task 10: Multilingual Semantic Textual Similarity (2014, neutral): “, 2006) and WordNet (Fellbaum, 1998).”