关键词：
patent
retrieval
composite-domain
perspective
double-consistency
expansion
word
embedding
摘要：
Patent prior art search uses dispersed information to retrieve all the relevant documents with strong ambiguity from the massive patent database. This challenging task con-sists in patent reduction and patent expansion. Existing stud-ies on patent reduction ignore the relevance between techni-cal characteristics and technical domains, and result in am-biguous queries. Works on patent expansion expand terms from external resource by selecting words with similar dis-tribution or similar semantics. However, this splits the rele-vance between the distribution and semantics of the terms. Besides, common repository hardly meets the requirement of patent expansion for uncommon semantics and unusual terms. In order to solve these problems, we first present a novel composite-domain perspective model which converts the technical characteristic of a query patent to a specific composite classified domain and generates aspect queries. We then implement patent expansion with double consistency by combining distribution and semantics simultaneously. We also propose to train semantic vector spaces via word em-bedding under the specific classified domains, so as to pro-vide domain-aware expanded resource. Finally, multiple re-trieval results of the same topic are merged based on perspec-tive weight and rank in the results. Our experimental results on CLEP-IP 2010 demonstrate that our method is very effec-tive. It reaches about 5.43% improvement in recall and nearly 12.38% improvement in PRES over the state-of-the-art. Our work also achieves the best performance balance in terms of recall, MAP and PRES.
欢迎来到三峡大学图书馆！
中文科技期刊
详细信息
