A study of query reformulation for patent prior art search with partial patent applications

© 2015 ACM. Patents are used by legal entities to legally protect their inventions and represent a multi-billion dollar industry of li- censing and litigation. In 2014, 326,033 patent applications were approved in the US alone - a number that has dou- bled in the past 15 years and which makes prior art search a daunting, but necessary task in the patent application pro- cess. In this work, we seek to investigate the efficacy of prior art search strategies from the perspective of the in- ventor who wishes to assess the patentability of their ideas prior to writing a full application. While much of the liter- ature inspired by the evaluation framework of the CLEF-IP competition has aimed to assist patent examiners in assess- ing prior art for complete patent applications, less of this work has focused on patent search with queries represent- ing partial applications. In the (partial) patent search set- ting, a query is often much longer than in other standard IR tasks, e.g., the description section may contain hundreds or even thousands of words. While the length of such queries may suggest query reduction strategies to remove irrelevant terms, intentional obfuscation and general language used in patents suggests that it may help to expand queries with ad- ditionally relevant terms. To assess the trade-offs among all of these pre-application prior art search strategies, we com- paratively evaluate a variety of partial application search and query reformulation methods. Among numerous find- ings, querying with a full description, perhaps in conjunction with generic (non-patent specific) query reduction methods, is recommended for best performance. However, we also find that querying with an abstract represents the best trade-off in terms of writing effort vs. retrieval efficacy (i.e., querying with the description sections only lead to marginal improve- ments) and that for such relatively short queries, generic query expansion methods help.