Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling

By Ira Leviant, Roi Reichart. 2015

76 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Analysis Methods in Neural Language Processing: A Survey (2018, background): “Multilingual and cross-lingual versions have also been collected (Leviant and Reichart, 2015; Cer et al., 2017).”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “Other striking findings include P@1 scores for Russian-Ukrainian (0.84 vs. 0.59), Czech-Slovak (0.82 vs. 0.59), Serbian-Croatian (0.78 vs. 0.56), or Danish-Norwegian (0.73 vs. 0.67).”
A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces (2019, methodology): “10We evaluate word similarities for DE, IT, RU, and HR on their respective SimLex datasets (Leviant and Reichart 2015; Mrkšić et al. 2017); there is no ES and TR SimLex.”
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints (2017, methodology): “Leviant and Reichart (2015) translated SimLex-999 to German, Italian and Russian, crowd-sourcing the similarity scores from native speakers of these languages.”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “For instance, the translations and reannotations of WordSim-353 and SimLex-999 (Leviant & Reichart, 2015) and the datasets from the SemEval-2017 task on multilingual word similarity (Camacho-Collados, Pilehvar, Collier, & Navigli, 2017) provide evaluation benchmarks for languages other than English.”
How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages? (2019, methodology): “Evaluation on Simlex and WordSim-353 We evaluate the quality of the grammatical-genderneutralized embeddings using two datasets for each language: SimLex-999 (Hill et al., 2015; Leviant and Reichart, 2015) and WordSim-353 (Finkelstein et al.”
Finnish resources for evaluating language model semantics (2017, background): “However, there are only few resources for evaluating the accuracy or validity of language models, particularly for less-spoken languages, due to language dependence of such resources (Leviant and Reichart, 2015).”