Cross-Lingual Latent Topic Extraction

90 citations recorded by the source corpus.

How researchers see this paper

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

Bilingual Word Embeddings from Parallel and Non-parallel Corpora for Cross-Language Text Classification (2016, methodology): “Extraction of cross-language latent topics or concepts use context-insensitive (Zhang et al., 2010) and context-sensitive methods (Vuli´c and Moens, 2014) to build word co-occurrence statistics for document representations.”
Translingual Document Representations from Discriminative Projections (2010, methodology): “PLSA-, LDA-, and CCA-based cross-lingual models have also been trained without the use of parallel or comparable documents, using only knowledge from a translation dictionary to achieve sharing of topics across languages (Haghighi et al., 2008; Jagarlamudi and Daumé, 2010; Zhang et al., 2010).”
Inducing Crosslingual Distributed Representations of Words (2012, background): “Development of crosslingual models (e.g., topic models (Zhang et al., 2010; Mimno et al., 2009)) has also attracted some attention.”
Applications of Topic Models (2017, background): “1Zhang et al. [2010] use topic-level soft constraints to achieve a similar effect.”