Comparing Complex Concepts with Transformers: Matching Patent Claims Against Natural Language Text
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911955230392320 |
|---|---|
| author | Blume, Matthias Heidari, Ghobad Hewel, Christoph |
| author_facet | Blume, Matthias Heidari, Ghobad Hewel, Christoph |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10351 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Comparing Complex Concepts with Transformers: Matching Patent Claims Against Natural Language Text Blume, Matthias Heidari, Ghobad Hewel, Christoph Computation and Language I.2.7 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. |
| title | Comparing Complex Concepts with Transformers: Matching Patent Claims Against Natural Language Text |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2407.10351 |