Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285196749> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4285196749 endingPage "59218" @default.
- W4285196749 startingPage "59205" @default.
- W4285196749 abstract "Patents provide inventors exclusive rights to their inventions by protecting their intellectual property rights. However, analyzing patent documents generally requires knowledge of various fields, considerable human labor, and expertise. Recent studies to alleviate this problem on patent analysis deal only with the analysis of claims and abstract parts, neglecting the descriptions that contain essential technical cores. Moreover, few studies use a deep learning approach to handle the entire patent analysis process, including preprocessing, summarization, and key-phrase generation. Therefore, we propose a novel multi-stage framework that can aid in analyzing patent documents by using the description part of the patent rather than abstracts or claims with deep learning. The framework comprises two stages: key-sentence extraction and key-phrase generation tasks. These stages are based on the T5 model structure, transformer-based architecture that uses a text-to-text approach. To further improve the framework’s performance, we employed two key factors: i) post-training the model with a patent-related raw corpus for encouraging the model’s comprehension of the patent domain, and ii) utilizing a text rank algorithm for efficient training based on the priority score of each sentence. We verified that our key-phrase generation method of the framework shows higher performance in both superficial and semantic evaluation than other extraction methods. In addition, we provided the validity and effectiveness of our methods through quantitative and qualitative analysis, demonstrating the practical functionality of our methods. We also provided a practical contribution to the patent analysis by releasing the framework as a demo system." @default.
- W4285196749 created "2022-07-14" @default.
- W4285196749 creator A5003145618 @default.
- W4285196749 creator A5026453749 @default.
- W4285196749 creator A5029547628 @default.
- W4285196749 creator A5033580486 @default.
- W4285196749 creator A5048597650 @default.
- W4285196749 creator A5049704678 @default.
- W4285196749 creator A5068060125 @default.
- W4285196749 date "2022-01-01" @default.
- W4285196749 modified "2023-09-30" @default.
- W4285196749 title "AI for Patents: A Novel yet Effective and Efficient Framework for Patent Analysis" @default.
- W4285196749 cites W1971579776 @default.
- W4285196749 cites W1989307299 @default.
- W4285196749 cites W2052371873 @default.
- W4285196749 cites W2062418945 @default.
- W4285196749 cites W2073398847 @default.
- W4285196749 cites W2106116881 @default.
- W4285196749 cites W2117130368 @default.
- W4285196749 cites W2133286915 @default.
- W4285196749 cites W2163013692 @default.
- W4285196749 cites W2198886427 @default.
- W4285196749 cites W2267496948 @default.
- W4285196749 cites W2493916176 @default.
- W4285196749 cites W2768660732 @default.
- W4285196749 cites W2789330408 @default.
- W4285196749 cites W2798723859 @default.
- W4285196749 cites W2799445970 @default.
- W4285196749 cites W2889270115 @default.
- W4285196749 cites W2913651615 @default.
- W4285196749 cites W2925065304 @default.
- W4285196749 cites W2963265326 @default.
- W4285196749 cites W2963351448 @default.
- W4285196749 cites W2970771982 @default.
- W4285196749 cites W2975532892 @default.
- W4285196749 cites W3022330581 @default.
- W4285196749 cites W3044968736 @default.
- W4285196749 cites W3145477840 @default.
- W4285196749 cites W3187058997 @default.
- W4285196749 cites W3209934712 @default.
- W4285196749 cites W3130090597 @default.
- W4285196749 doi "https://doi.org/10.1109/access.2022.3176877" @default.
- W4285196749 hasPublicationYear "2022" @default.
- W4285196749 type Work @default.
- W4285196749 citedByCount "1" @default.
- W4285196749 countsByYear W42851967492023 @default.
- W4285196749 crossrefType "journal-article" @default.
- W4285196749 hasAuthorship W4285196749A5003145618 @default.
- W4285196749 hasAuthorship W4285196749A5026453749 @default.
- W4285196749 hasAuthorship W4285196749A5029547628 @default.
- W4285196749 hasAuthorship W4285196749A5033580486 @default.
- W4285196749 hasAuthorship W4285196749A5048597650 @default.
- W4285196749 hasAuthorship W4285196749A5049704678 @default.
- W4285196749 hasAuthorship W4285196749A5068060125 @default.
- W4285196749 hasBestOaLocation W42851967491 @default.
- W4285196749 hasConcept C108583219 @default.
- W4285196749 hasConcept C114419676 @default.
- W4285196749 hasConcept C154945302 @default.
- W4285196749 hasConcept C170858558 @default.
- W4285196749 hasConcept C204321447 @default.
- W4285196749 hasConcept C23123220 @default.
- W4285196749 hasConcept C26517878 @default.
- W4285196749 hasConcept C2776224158 @default.
- W4285196749 hasConcept C2777530160 @default.
- W4285196749 hasConcept C34736171 @default.
- W4285196749 hasConcept C38652104 @default.
- W4285196749 hasConcept C41008148 @default.
- W4285196749 hasConceptScore W4285196749C108583219 @default.
- W4285196749 hasConceptScore W4285196749C114419676 @default.
- W4285196749 hasConceptScore W4285196749C154945302 @default.
- W4285196749 hasConceptScore W4285196749C170858558 @default.
- W4285196749 hasConceptScore W4285196749C204321447 @default.
- W4285196749 hasConceptScore W4285196749C23123220 @default.
- W4285196749 hasConceptScore W4285196749C26517878 @default.
- W4285196749 hasConceptScore W4285196749C2776224158 @default.
- W4285196749 hasConceptScore W4285196749C2777530160 @default.
- W4285196749 hasConceptScore W4285196749C34736171 @default.
- W4285196749 hasConceptScore W4285196749C38652104 @default.
- W4285196749 hasConceptScore W4285196749C41008148 @default.
- W4285196749 hasFunder F4320322120 @default.
- W4285196749 hasLocation W42851967491 @default.
- W4285196749 hasOpenAccess W4285196749 @default.
- W4285196749 hasPrimaryLocation W42851967491 @default.
- W4285196749 hasRelatedWork W132250100 @default.
- W4285196749 hasRelatedWork W1794016765 @default.
- W4285196749 hasRelatedWork W2093597205 @default.
- W4285196749 hasRelatedWork W2389846579 @default.
- W4285196749 hasRelatedWork W2392495745 @default.
- W4285196749 hasRelatedWork W2401226416 @default.
- W4285196749 hasRelatedWork W2725657302 @default.
- W4285196749 hasRelatedWork W3044420261 @default.
- W4285196749 hasRelatedWork W4313289316 @default.
- W4285196749 hasRelatedWork W2549211093 @default.
- W4285196749 hasVolume "10" @default.
- W4285196749 isParatext "false" @default.
- W4285196749 isRetracted "false" @default.
- W4285196749 workType "article" @default.