The information available in languages other than English on the World Wide Web is increasing significantly. According to a report from Computer Economics [1], 54% of Internet users are English speaking. However, it is predicted that there will be only 60% increase in Internet users among English speakers but there will be 150% growth among nonEnglish speakers for the next five years. By 2005, ...

We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts) into a coherent common representation including multi-level knowledge (concepts, relations and events). Beyond standard information fusion, we exploited video extraction results and significantly improved text Information Extraction. We further extended our methods to multi-lin...

We present a filtering mechanism using two cross-lingual information extraction (CLIE) systems for improving document relevance of cross-lingual information retrieval (CLIR) for queries conforming to predefined templates. Experiments on retrieving Chinese documents in response to English GALE arrest queries show that this approach can obtain a 12.7% absolute improvement in relevance (representi...

The current study examines whether bilingual word recognition in spoken sentences is influenced by cross-lingual phonological similarity. ERPs were measured while GermanEnglish bilinguals listened to German sentences. Target words in the sentences were either German-English homophones (e.g., eagle – Igel ‘hedgehog’), German words that were phonologically closely related to English words (e.g., ...

Cross Lingual Word Semantic (CLWS) similarity is defined as a task to find the semantic similarity between two words across languages. Semantic similarity has been very popular in computing the similarity between two words in same language. CLWS similarity will prove to be very effective in the area of Cross Lingual Information Retrieval, Machine Translation, Cross Lingual Word Sense Disambigua...

We present a new data-driven approach for enhancing the extraction of translation equivalents from comparable corpora which exploits bilingual lexico-semantic knowledge harvested from a parallel corpus. First, the bilingual lexicon obtained from word-aligning the parallel corpus replaces an external seed dictionary, making the approach knowledge-light and portable. Next, instead of using simple...

We present a framework for concept-based, cross-lingual information retrieval (CLIR) in the medical domain, which is under development in the MUCHMORE project. Our approach is based on using the Unified Medical Language System (UMLS) as the primary source of semantic data, whereby documents and queries are annotated with multiple layers of linguistic information. Linguistic processing includes ...

Following the growing trend in the semantics community towards models adapted to specific applications, the SemEval-2 Cross-Lingual Lexical Substitution and Word Sense Disambiguation tasks address the disambiguation needs of Machine Translation (MT). The experiments conducted in this study aim at assessing whether the proposed evaluation protocol and methodology provide a fair estimate of the a...

This paper gives an overview of the NTCIR-5 Cross-Lingual Question Answering Task (CLQA1), an evaluation campaign for Cross-Lingual Question Answering technology. This evaluation was carried out in June 2005. In CLQA1, we aimed to promote research on cross-lingual Question Answering technology mainly for East Asian languages. As the first attempt, we conducted evaluations of five subtasks: JE, ...

Cross-lingual speaker adaptation with limited adaptation data has many applications such as use in speech-to-speech translation systems. Here, we focus on cross-lingual adaptation for statistical speech synthesis (SSS) systems using limited adaptation data. To that end, we propose two techniques exploiting a bilingual Turkish-English speech database that we collected. In one approach, speaker-s...