This article presents a comparison of the accuracy of a number of different approaches for identifying cross language term equivalents (translations). The methods investigated are on the one hand associative measures, commonly used in word-space models or in Information Retrieval and on the other hand a Statistical Machine Translation (SMT) approach. I have performed tests on six language pairs, using the JRC-Acquis parallel corpus as training material and Eurovoc as a gold standard. The SMT approach is shown to be more effective than the associative measures. The best results are achieved by taking a weighted average of the scores of the SMT approach and disparate associative measures. 1

This paper presents a novel approach to the problem of hedge detection, which involves the identification of so-called hedge cues for labeling sentences as certain or uncertain. This is the classification problem for Task 1 of the CoNLL-2010 Shared Task, which focuses on hedging in biomedical literature. We here propose to view hedge detection as a simple disambiguation problem, restricted to words that have previously been observed as hedge cues. Applying an SVM classifier, the approach achieves the best published results so far for sentence-level uncertainty prediction on the Shared Task test data. We also show that the technique of random indexing can be successfully applied for compressing the dimensionality of the original feature space by several orders of magnitude, while at the same time yielding better classifier performance. 1

This paper presents a very simple and effective approach to using parallel corpora for automatic bilingual lexicon acquisition. The approach, which uses the Random Indexing vector space methodology, is based on finding correlations between terms based on their distributional characteristics. The approach requires a minimum of preprocessing and linguistic knowledge, and is efficient, fast and scalable. In this paper, we explain how our approach differs from traditional cooccurrence-based word alignment algorithms, and we demonstrate how to extract bilingual lexica using the Random Indexing approach applied to aligned parallel data. The acquired lexica are evaluated by comparing them to manually compiled gold standards, and we report overlap of around 60%. We also discuss methodological problems with evaluating lexical resources of this kind.

This paper presents a very simple and effective approach to using parallel corpora for automatic bilingual lexicon acquisition. The approach, which uses the Random Indexing vector space methodology, is based on finding correlations between terms based on their distributional characteristics. The approach requires a minimum of preprocessing and linguistic knowledge, and is efficient, fast and scalable. In this paper, we explain how our approach differs from traditional cooccurrence-based word alignment algorithms, and we demonstrate how to extract bilingual lexica using the Random Indexing approach applied to aligned parallel data. The acquired lexica are evaluated by comparing them to manually compiled gold standards, and we report overlap of around 60%. We also discuss methodological problems with evaluating lexical resources of this kind.

Abstract. This experiment tests a simple, scalable, and effective approach to building a domain-specific translation lexicon using distributional statistics over parallellized bilingual corpora. A bilingual lexicon is extracted from aligned Swedish-French data, used to translate CLEF topics from Swedish to French, which resulting French queries are then in turn used to retrieve documents from the French language CLEF collection. The results give 34 of fifty queries on or above median for the “precision at 1000 documents ” recall oriented score; with many of the errors possible to handle by the use of string-matching and cognate search. We conclude that the approach presented here is a simple and efficient component in an automatic query translation system. 1 Lexical Resources Should Be Dynamic Multilingual information access applications, which are driven by modeling lexical correspondences between different human languages, are obviously reliant on lexical resources to a high degree — the quality of the lexicon is the main