作者: K. L. Kwok
关键词: Cross-language information retrieval 、 Cross language retrieval 、 Natural language processing 、 Selection (linguistics) 、 Phrase 、 Linguistics 、 Computer science 、 Weighting 、 Word (computer architecture) 、 Artificial intelligence 、 Term (logic)
摘要: We investigated using the LDC English/Chinese bilingual wordlists for English-Chinese cross language retrieval. It is shown that Chinese-to-English wordlist can be considered as both a phrase and word dictionary, preferable to English-to-Chinese version in terms of translations translation selection. Additional techniques such target corpus frequency-based term selection weighting were employed. Experiments show over 70% monolingual effectiveness achievable TREC Chinese retrieval environment with short queries few English words.