We participated in the Bilingual Document Alignment shared task of WMT 2016 with the intent of testing plain cross-lingual information retrieval platform built on top of the Apache Lucene framework. We devised a number of interesting variants, including one that only considers the URLs of the pages, and that offers-without any heuristic-surprisingly high performances. We finally submitted the output of a system that combines two informations (text and url) from documents and a post-treatment for an accuracy that reaches 92% on the development dataset distributed for the shared task.

We investigate the reranking of the output of several distributional approaches on the Bilingual Lexicon Induction task. We show that reranking an n-best list produced by any of those approaches leads to very substantial improvements. We further demonstrate that combining several n-best lists by reranking is an effective way of further boosting performance.

Identifying translations in comparable corpora is a challenge that has attracted many researchers since a long time. It has applications in several applications including Machine Translation and Cross-lingual Information Retrieval. In this study we compare three state-of-the-art approaches for these tasks: the so-called context-based projection method, the projection of monolingual word embeddings, as well as a method dedicated to identify translations of rare words. We carefully explore the hyper-parameters of each method and measure their impact on the task of identifying the translation of English words in Wikipedia into French. Contrary to the standard practice, we designed a test case where we do not resort to heuristics in order to pre-select the target vocabulary among which to find translations, therefore pushing each method to its limit. We show that all the approaches we tested have a clear bias toward frequent words. In fact, the best approach we tested could identify the translation of a third of a set of frequent test words, while it could only translate around 10% of rare words.

Each entry (concept) in DBpedia comes along a set of surface strings (property rdfs:label) which are possible realizations of the concept being described. Currently, only a fifth of the English DBpedia entries have a surface string in French, which severely limits the deployment of Semantic Web Annotation for this language. In this paper, we investigate the task of identifying missing translations, contrasting two projective approaches. We show that the problem is actually challenging, and that a carefully engineered baseline is not easy to outperform.

No abstract