Welcome to xLiMe Semantic Integrator
A framework developed in work page Cross-Media Semantic Intgeration (WP4) as a part of xLiMe Project to collect, integrate, search and recommend different dimensions of media content (e.g. News, TV, Social Media etc.).
Provides simple keyword and advanced vector-space model based search for finding relevant content in News, Social Media and TV.
Provides monolingual and cross-lingual document comparison using monolingual and bilingual word distributed representations (i.e. embeddings).
Provides content based recommendation of the articles from different media based on input article.
Support analytics over the content from different media stored in the repositories.
A. Mogadala and A. Rettinger. Bilingual Word Embeddings from Parallel and Non-parallel Corpora for Cross-Language Text Classification. In 15th North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), San Diego, California, USA. (2016)
A. Mogadala and A.Rettinger. Multi-Modal Correlated Centroid Space for Multi-Lingual Cross-Modal Retrieval. In 37th European Conference on Information Retrieval (ECIR), Vienna, Austria (2015).
The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 611346.