Quantifying the Challenges in Parsing Patent Claims

Abstract

In this paper, we aim to verify and quantify the challenges of patent claim processing that have been identified in the literature. We focus on the following three challenges that, judging from the numbers of mentions in papers concerning patent analysis and patent retrieval, are central to patent claim processing: (1) The length of sentences is much longer than for general language use; (2) Many novel terms are introduced in patent claims that are difficult to understand; (3) The syntactic structure of patent claims is complex. We find that the challenges of patent claim processing that are related to syntactic structure are much more problematic than the challenges at the vocabulary level. The sentence length issue only causes problems indirectly by resulting in more structural ambiguities for longer noun phrases.