Retrieving research papers and patents is important for any researcher assessing the scope of a field with high industrial relevance. However, the terms used in patents are often more abstract or creative than those used in research papers, because they are intended to widen the scope of claims. Therefore, a method is required for translating scholarly terms into patent terms. In this paper, we propose six methods for translating scholarly terms into patent terms using two synonym extraction methods: a statistical machine translation (SMT)-based method and a distributional similarity (DS)-based method. We conducted experiments to confirm the effectiveness of our method using the dataset of the Patent Mining Task from the NTCIR-7 Workshop. The aim of the task was to classify Japanese language research papers (pairs of titles and abstracts) using the IPC system at the subclass (third level), main group (fourth level), and subgroup (the fifth and most detailed level). The results showed that an SMT-based method (SMT_ABST+IDF) performed best at the subgroup level, whereas a DS-based method (DS+IDF) performed best at the subclass level.

Many of the Japanese ideographs (Chinese characters) have a few meanings. Such ambiguities should be identified by using their contextual information. For example, we have an ideograph which has two pronunciations, /hitai/ and /gaku/, the former means a forehead of the human body and the latter has two meanings, an amount of money and a picture frame. Conventional methods for such a disambiguation problem have been using statistical methods with co-occurrence of words in their context. In this research, Contextual Dynamic Network Model is developed using the Associative Concept Dictionary which includes semantic relations among concepts/words and the relations can be represented with quantitative distances. In this model, an interactive activation method is used to identify a word’s meaning on the Contextual Semantic Network where the activation on the network is calculated using the distances. The proposed method constructs dynamically the Contextual Semantic Network according to the input words sequentially that appear in the sentence including an ambiguous word.