Toward any-language zero-shot topic classification of textual documents

DOI10.1016/J.ARTINT.2019.02.002MaRDI QIDQ2321313zbMATH OpenOpenAlexWikidataFDO

Authors Yangqiu Song, Shyam Upadhyay, Haoruo Peng, Stephen Mayhew, Dan Roth

Publication date 28 August 2019

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2019.02.002

zbMATH Keywords

cross-lingual text classificationmultilingual text classificationsemantic supervisionzero-shot text classification

Mathematics Subject Classification ID

Natural language processing (68T50)

Recommendations

• Lightweight random indexing for polylingual text classification
• Transductive discriminative dictionary learning approach for zero-shot classification
• A co-classification approach to learning from multilingual corpora
• Automatic document classification based on latent semantic analysis
• Word-class embeddings for multiclass text classification

Cites work

• scientific article; zbMATH DE number 1175490 (Why is no real title available?)
• 10.1162/jmlr.2003.3.4-5.993
• A co-classification approach to learning from multilingual corpora
• BabelNet: the automatic construction, evaluation and application of a wide-coverage multilingual semantic network
• Human-level concept learning through probabilistic program induction
• LIBLINEAR: a library for large linear classification
• Natural language processing (almost) from scratch
• Wikipedia-based semantic interpretation for natural language processing
• \textsc{Nasari}: integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities

Cited in

(1)

• Lightweight random indexing for polylingual text classification

Describes a project that uses

Uses Software

• WordNet
• LIBLINEAR
• RCV1
• word2vec
• Nasari
• BabelNet
• Omniglot
• Europarl

This page was built for publication: Toward any-language zero-shot topic classification of textual documents

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2321313)