In this paper we explore a new method for vocabulary enhancement in cross-language retrieval. The focus is on whether we can improve upon dictionary-based retrieval, machine translation of queries, or the use of a bilingual lexicon derived from parallel corpus alignment. All experiments are done with the NACSIS collection of Japanese scientific abstracts with titles and author-assigned keywords...

It is claimed that bilingual children have two separate linguistic systems from early ages. Over the past decades, linguists carried out a number of studies to test the validity of the claim. They explored bilingual children’s code-mixing in correlation with a variety of linguistic elements, such as lexicon, syntax, phonology in different contexts, concluding that bilingual children had separat...

This paper demonstrates one efficient technique in extracting bilingual word pairs from non-parallel but comparable corpora. Instead of using the common approach of taking high frequency words to build up the initial bilingual lexicon, we show contextually relevant terms that co-occur with cognate pairs can be efficiently utilized to build a bilingual dictionary. The result shows that our model...

This paper outlines a strategy to build new bilingual dictionaries from existing resources. The method is based on two main tasks: first, a new set of bilingual correspondences is generated from two available bilingual dictionaries. Second, the generated correspondences are validated by making use of a bilingual lexicon automatically extracted from non-parallel, and comparable corpora. The qual...

This paper introduces an experimental system which can extract translations of words and phrases from the Internet through alignment on parallel WWW pages. The automatic extraction takes place online, is language independent and incrementally formed after a post-editing step by a human being. Actually the experimental system can extract words and phrases between pairs of the languages English, ...

This paper describes our experiment on two cross-lingual and one monolingual English text retrievals at CLEF in the ad-hoc track. The cross-language task includes the retrieval of English documents in response to queries in two most widely spoken Indian languages, Hindi and Bengali. For our experiment, we had access to a HindiEnglish bilingual lexicon, ’Shabdanjali’, consisting of approx. 26K H...

In this article we address the task of cross-lingual sentiment lexicon learning, which aims to automatically generate sentiment lexicons for the target languages with available English sentiment lexicons. We formalize the task as a learning problem on a bilingual word graph, in which the intra-language relations among the words in the same language and the interlanguage relations among the word...

The task of unsupervised lexicon induction is to find translation pairs across monolingual corpora. We develop a novel method that creates seed lexicons by identifying cognates in the vocabularies of related languages on the basis of their frequency and lexical similarity. We apply bidirectional bootstrapping to a method which learns a linear mapping between context-based vector spaces. Experim...

We present a new language pair agnostic approach to inducing bilingual vector spaces from non-parallel data without any other resource in a bootstrapping fashion. The paper systematically introduces and describes all key elements of the bootstrapping procedure: (1) starting point or seed lexicon, (2) the confidence estimation and selection of new dimensions of the space, and (3) convergence. We...