Method evidence record
Cross-lingual Text Analysis
Cross-lingual text analysis lets you compare and analyse texts written in different languages within a shared vector space. Building on multilingual representation learning surveyed by Conneau et al. (2020) and Pires et al. (2019), it maps documents from several languages into one common embedding space so multilingual corpora can be studied together.
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
Cross-lingual Text Analysis (Multilingual Representation Learning)
Taxonomic method record · process-pipeline / text-mining
- Conneau, A. et al. (2020). Unsupervised Cross-lingual Representation Learning at Scale. Proceedings of ACL. · DOI 10.18653/v1/2020.acl-main.747
- Pires, T., Schlinger, E. & Garrette, D. (2019). How Multilingual is Multilingual BERT? Proceedings of ACL. · DOI 10.18653/v1/P19-1493
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
No curated claims yet
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.