Coarse-grained Cross-lingual Alignment of Comparable Texts with Topic Models and Encyclopedic Knowledge
This addresses the challenge of aligning thematic content across languages for applications like multilingual document analysis, though it appears incremental as it builds on existing methods and data.
The paper tackles the problem of coarse-grained cross-lingual alignment of comparable texts by aligning segments discussing the same themes across languages, achieving state-of-the-art performance in both monolingual and cross-lingual evaluations.
We present a method for coarse-grained cross-lingual alignment of comparable texts: segments consisting of contiguous paragraphs that discuss the same theme (e.g. history, economy) are aligned based on induced multilingual topics. The method combines three ideas: a two-level LDA model that filters out words that do not convey themes, an HMM that models the ordering of themes in the collection of documents, and language-independent concept annotations to serve as a cross-language bridge and to strengthen the connection between paragraphs in the same segment through concept relations. The method is evaluated on English and French data previously used for monolingual alignment. The results show state-of-the-art performance in both monolingual and cross-lingual settings.