Comparing Complex Concepts with Transformers: Matching Patent Claims Against Natural Language Text
This addresses a challenge in intellectual property management by improving computer-based comparison of patent claims, though it is incremental as it builds on existing LLM methods.
The paper tackled the problem of comparing patent claims, which use specialized language, against other text like patent specifications using natural language processing, and found that two new LLM-based approaches provided substantially better performance than previous methods.
A key capability in managing patent applications or a patent portfolio is comparing claims to other text, e.g. a patent specification. Because the language of claims is different from language used elsewhere in the patent application or in non-patent text, this has been challenging for computer based natural language processing. We test two new LLM-based approaches and find that both provide substantially better performance than previously published values. The ability to match dense information from one domain against much more distributed information expressed in a different vocabulary may also be useful beyond the intellectual property space.