BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network

By Roberto Navigli, Simone Paolo Ponzetto. 2012

1,754 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Molecular Biology

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations (2018, methodology): “The same applies to SW2V, which leverages knowledge from a sig-niﬁcantly larger lexical resource, i.e., BabelNet (Navigli and Ponzetto, 2012).”
Spatio-temporal video autoencoder with differentiable memory (2015, methodology): “In particular, we describe a spatio-temporal video autoencoder integrating a differentiable short-term memory module whose (unsupervised) training is geared towards motion estimation and prediction Horn & Schunck (1994).”
Datasheet for the Pile (2022, methodology): “EuroParl: EuroParl has been extensively used, including by [Bouma, 2009, Koehn, 2009, Heafield, 2011, Navigli and Ponzetto, 2012, Cho et al., 2014].”
Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge (2018, neutral): “Such knowledge may be commonsense knowledge or factual background knowledge about entities and events that is not explicitly expressed but can be found in a knowledge base such as ConceptNet (Speer et al., 2017), BabelNet (Navigli and Ponzetto, 2012), Freebase (Tanon et al., 2016) or domain-specific”
Learning from Noisy Labels with Distillation (2017, methodology): “For Species and Artifacts, we cross-link their entities with ImageNet [17] synsets using the BabelNet dataset [15], which is a multilingual database linking various linguistic datasets, including WordNet and Wikipedia.”
What Substitutes Tell Us - Analysis of an “All-Words” Lexical Substitution Corpus (2014, methodology): “A number of technical solutions have been suggested regarding the second problem (Ando and Zhang, 2005; Navigli and Ponzetto, 2012), but not for the ﬁrst.”
Evolution of Semantic Similarity—A Survey (2020, methodology): “• BabelNet[66] is a lexical resource that combines WordNet with data available on Wikipedia for each synset .”
Entity Linking meets Word Sense Disambiguation: a Unified Approach (2014, methodology): “…creation of large semi-structured resources, such as Wikipedia, and knowledge resources built from them (Hovy et al., 2013), such as BabelNet (Navigli and Ponzetto, 2012a), DBpedia (Auer et al., 2007) and YAGO2 (Hoffart et al., 2013), has favoured the emergence of new tasks, such as Entity…”
Linked Disambiguated Distributional Semantic Networks (2016, methodology): “Our method takes as input: 1. a PCZ T = {(ji, Rji , Hji)}where ji is a sense identifier (i.e. mouse:NN:1), Rji the set of its semantically related senses (i.e. Rji = {keyboard:NN:1, computer:NN:0, . . .} and Hji the set of its hypernym senses (i.e. Hji = {equipment:NN:3, . . .}; 2. a LR W : we exper”
De-Conflated Semantic Representations (2016, methodology): “The three best-performing systems in the task are Meerkat Maﬁa (Kashyap et al., 2014) ( r = 37 .”
Aligning Cross-Lingual Entities with Multi-Aspect Information (2019, background): “, 2016), and BabelNet (Navigli and Ponzetto, 2012), which typically represent realworld knowledge as separately-structured monolingual KGs.”
Biases in Large Language Models: Origins, Inventory, and Discussion (2023, methodology): “For this mapping, we utilized BabelNet [97, 98], a large multilingual lexical-semantic knowledge graph that merges encyclopedic and lexicographic information in hundreds of languages.”
Automatic Keyphrase Extraction: A Survey of the State of the Art (2014, methodology): “We recommend that background knowledge be extracted from external lexical databases (e.g., YAGO2 (Suchanek et al., 2007), Freebase (Bol-lacker et al., 2008), BabelNet (Navigli and Ponzetto, 2012)) to address the four types of errors discussed above.”
From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers (2020, background): “…discrete text representations include machine translation (MT) of target language text to the source language (or vice-versa) (Mayhew et al., 2017; Eger et al., 2018), and grounding texts from both languages in multilingual knowledge bases (KBs) (Navigli and Ponzetto, 2012; Lehmann et al., 2015).”
Stop Clickbait: Detecting and preventing clickbaits in online news media (2016, methodology): “For a given link, we used BabelNet [15] 6 to expand its BlockTags or ClickTags sets.”
Learning and Evaluating Emotion Lexicons for 91 Languages (2020, background): “A promising direction would be to combine a multilingual sense inventory such as BABELNET (Navigli and Ponzetto, 2012) with sense embeddings (Camacho-Collados and Pilehvar, 2018).”
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison (2017, methodology): “BabelNet includes Wikipedia as one of its main sources of information.”
DOCK: Detecting Objects by Transferring Common-Sense Knowledge (2018, background): “Our field has witnessed the rise of several interesting knowledge bases, including ConceptNet [23], BabelNet [29], WordNet [27], WebChild [38], Visual Genome [19], ImSitu [44], etc.”