Industrial Technology Research Institute

Institute for Information Industry

Jason S Chang

Wen-Tai Hsieh

Tsun Ku

Wen-Nan Wang

Ching-Hsien Li

Yu-Ru Chen

Jian-Cheng Wu

Hung-Ting Hsieh

Chien-Cheng Wu

A search system for collecting aliases associated with an entity name, includes a storage module configured to store at least one first lexical pattern, a search module coupled to the storage module and configured to obtain a plurality of first snippets from a database according to the entity name, and an alias extracting module coupled to the storage module and the search module separately and configured to, according to the entity name and the first lexical pattern, determine whether any first alias exists in the first snippets. If a first alias exists, the alias extracting module extracts it out and stores it in the storage module.

System and method for searching aliases associated with an entity

A method for constructing a Chinese dictionary is disclosed, including determining a probability for nominalization of a Chinese term with a given collocation term according to a determination rule and the correlation between the Chinese term and its corresponding collocations, wherein the Chinese term is determined to be a verb part-of-speech. The method further includes modifying the verb part-of-speech of the Chinese term with the given collocation term to an appropriate part-of-speech when the probability for nominalization of the Chinese term with the given collocation term is higher than a predetermined value, and storing the correlation between the Chinese term, the given collocation term and the appropriate part-of-speech in a storage device.

Method for constructing Chinese dictionary and apparatus and storage media using the same

A method for text alignment of a first document and a second document that is a translation version of the first document. The method first divides paragraphs of the first and second documents into sub-sentential segments according to the punctuations in the language of the first and second documents. Each of sub-sentential segments corresponds to a plurality of words. After the sub-sentential segmenting process, pairs of alignment units are summarized from the first and second documents. The alignment units in the first and second documents are then aligned and scored mainly based on the probability of corresponding punctuations. To increase the alignment accuracy, the pairs of alignment units can also be aligned and scored based on at least one of length corresponding probability, match type probability, and lexical information. The method allows for fast, reliable, and robust alignment of document and translated document in two disparate languages.

Method for extracting translations from translated texts using punctuation-based sub-sentential alignment

Growing community of inventors

Hsinchu, Taiwan

Jason S Chang