No abstract

No abstract

Cross domain recommendations are of growing importance in the research community. An application of particular interest is to recommend a set of relevant research papers as citations for a given patent. This paper proposes an approach for cross-domain citation recommendation based on the Hybrid Topic Model and Co-Citation Selection. Using the topic model, relevant terms from documents could be clustered into the same topics. In addition, the Co-Citation Selection technique will help select citations based on a set of highly similar patents. To evaluate the Author performance, we compared our proposed approach with the traditional baseline approaches using a corpus of patents collected for different technological fields of biotechnology, environmental technology, medical technology and nanotechnology. Experimental results show our cross domain citation recommendation yields a higher performance in predicting relevant publication citations than all baseline approaches.

Abstract. An extraction tool, nowadays, has become useful for text mining researchers to find keywords and keyphrases from the documents. Performing keywords and keyphrases extraction for cross-domain information are more challenging since both domains of interest are different in word usage. In this paper, two popular keyphrases extraction tools, Maui and Carrot, are investigated, for extracting terms from cross-domain document databases. The characteristic of keywords or phrases matching among different domain collections is presented and used for determining the keyphrase extraction tool for patent documents and scientific publications. In our experiment, matching between a patent and its cited publication are the key point. For evaluation, the performance of cross-domain matching is measured by comparing the similarity measure among those extraction tool results. The experimental results show that Maui tool proves to be the appropriate keyphrases extraction tool with its best performance measured by Cosine similarity of 3.31% when compared with Carrot tool for cross-domain document collections matching.

No abstract