PatentEdits: Framing Patent Novelty as Textual Entailment
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912127972802560 |
|---|---|
| author | Lee, Ryan Spangher, Alexander Ma, Xuezhe |
| author_facet | Lee, Ryan Spangher, Alexander Ma, Xuezhe |
| contents | A patent must be deemed novel and non-obvious in order to be granted by the US Patent Office (USPTO). If it is not, a US patent examiner will cite the prior work, or prior art, that invalidates the novelty and issue a non-final rejection. Predicting what claims of the invention should change given the prior art is an essential and crucial step in securing invention rights, yet has not been studied before as a learnable task. In this work we introduce the PatentEdits dataset, which contains 105K examples of successful revisions that overcome objections to novelty. We design algorithms to label edits sentence by sentence, then establish how well these edits can be predicted with large language models (LLMs). We demonstrate that evaluating textual entailment between cited references and draft sentences is especially effective in predicting which inventive claims remained unchanged or are novel in relation to prior art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13477 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PatentEdits: Framing Patent Novelty as Textual Entailment Lee, Ryan Spangher, Alexander Ma, Xuezhe Computation and Language Artificial Intelligence Computers and Society Information Retrieval A patent must be deemed novel and non-obvious in order to be granted by the US Patent Office (USPTO). If it is not, a US patent examiner will cite the prior work, or prior art, that invalidates the novelty and issue a non-final rejection. Predicting what claims of the invention should change given the prior art is an essential and crucial step in securing invention rights, yet has not been studied before as a learnable task. In this work we introduce the PatentEdits dataset, which contains 105K examples of successful revisions that overcome objections to novelty. We design algorithms to label edits sentence by sentence, then establish how well these edits can be predicted with large language models (LLMs). We demonstrate that evaluating textual entailment between cited references and draft sentences is especially effective in predicting which inventive claims remained unchanged or are novel in relation to prior art. |
| title | PatentEdits: Framing Patent Novelty as Textual Entailment |
| topic | Computation and Language Artificial Intelligence Computers and Society Information Retrieval |
| url | https://arxiv.org/abs/2411.13477 |