Incorporating Pronunciation Variation into Extraction of Transliterated-term Pairs from Web Corpora

Generating Paired Transliterated-cognates Using Multiple Pronunciation Characteristics from Web corpora

A novel approach to automatically extracting paired transliterated-cognates from Web corpora is proposed in this paper. One of the most important issues addressed is that of taking multiple pronunciation characteristics into account. Terms from various languages may pronounce very differently. Incorporating the knowledge of word origin may improve the pronunciation accuracy of terms. The accura...

Incorporating Pronunciation Variation into Different Strategies of Term Transliteration

Term transliteration addresses the problem of converting terms in one language into their phonetic equivalents in the other language via spoken form. It is especially concerned with proper nouns, such as personal names, place names and organization names. Pronunciation variation refers to pronunciation ambiguity frequently encountered in spoken language, which has a serious impact on term trans...

Constructing Transliteration Lexicons from Web Corpora

This paper proposes a novel approach to automating the construction of transliterated-term lexicons. A simple syllable alignment algorithm is used to construct confusion matrices for cross-language syllable-phoneme conversion. Each row in the confusion matrix consists of a set of syllables in the source language that are (correctly or erroneously) matched phonetically and statistically to a syl...

應用混淆音矩陣之中英文音譯詞組自動抽取 (Automatic Transliterated-term Extraction Using Confusion Matrix from Non-parallel Corpora) [In Chinese]

Multiword Named Entities Extraction from Cross-Language Text Re-use

In practice, many named entities (NEs) are multiword. Most of the research, done on mining the NEs from the comparable corpora, is focused on the single word transliterated NEs. This work presents an approach to mine Multiword Named Entities (MWNEs) from the text re-use document pairs. Text re-use, at document level, can be seen as noisy parallel or comparable text based on the level of obfusca...