Filters








10,774 Hits in 4.1 sec

Developing a Methodology of Structuring and Layering Technological Information in Patent Documents through Natural Language Processing

Taeyeoun Roh, Yujin Jeong, Byungun Yoon
2017 Sustainability  
In this research, we structure meaningful keyword sets related to technological information from patent documents; then we layer the keywords, depending on the level of information.  ...  Second, the technological information is structured by considering the information types, and the keywords in each type are layered through natural language processing.  ...  field extracted from one patent.  ... 
doi:10.3390/su9112117 fatcat:tkl74plh6ve3lau62xclhqyomm

Open Relation Extraction in Patent Claims with a Hybrid Network

Boting Geng, Wenqing Wu
2021 Wireless Communications and Mobile Computing  
Due to lengthy sentences, crossdomain technical terms, and complex structure of patent claims, it is extremely difficult to extract open triples with traditional methods of Natural Language Processing  ...  triples from patent claims with a hybrid neural network architecture based on multihead attention mechanism.  ...  [12] proposed an extraction of verbal content relations from patent claims using deep syntactic structures. Fantoni et al.  ... 
doi:10.1155/2021/5547281 fatcat:mduxto5zzzacfanawwrbg4acay

Query Terms Extraction from Patent Document for Invalidity Search

Kazuya Konishi
2005 NTCIR Conference on Evaluation of Information Access Technologies  
We extracted query terms from the topic claim, and expanded query terms extracted from sentences explained in the patent document including the topic claim.  ...  The explanation sentences were extracted by the method based on pattern matching and by the method based on the longest common subsequence length.  ...  Figure 1 shows the structure of patent. A patent consists of an "International Patent Classification (IPC) code," "abstract," "claims," "detailed description," and so on.  ... 
dblp:conf/ntcir/Konishi05 fatcat:rmzrsfwpuja5thxjc3ivzsqflm

Applying Information Extraction for Patent Structure Analysis

Masayuki Okamoto, Zifei Shan, Ryohei Orihara
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
In this paper, we propose an informationextraction-based technique to grasp the patent claim structure.  ...  Patent engineers are spending significant time analyzing patent claim structures to grasp the range of technology covered or to compare similar patents in the same patent family.  ...  CLAIM STRUCTURE EXTRACTION In this section, we propose an information extraction-based patent claim structure extraction method.  ... 
doi:10.1145/3077136.3080698 dblp:conf/sigir/OkamotoSO17 fatcat:ywiadv6v7zf7xntrmjrdxt7uz4

Patent claim decomposition for improved information extraction

Peter Parapatics, Michael Dittenbach
2009 Proceeding of the 2nd international workshop on Patent information retrieval - PaIR '09  
The extracted claim parts are organized in a tree structure in order to retain the information on how they are related to each other.  ...  Patent claims, although subject to a number of rigid constraints and therefore pressed into foreseeable structures, are written in a very domain-specific and almost artificial language common information  ...  Structure-Based Conceptual Search In [YS08] a similarity measure for patent claims is computed by comparing the structure of conceptual graphs extracted from the claims.  ... 
doi:10.1145/1651343.1651351 fatcat:55v7yhfwtjfllpyx7eyjt32una

Summarization, Simplification, and Generation: The Case of Patents [article]

Silvia Casola, Alberto Lavelli
2021 arXiv   pre-print
While solving these tasks has important practical applications - given patents' centrality in the R&D process - patents' idiosyncrasies open peculiar challenges to the current NLP state of the art.  ...  We survey Natural Language Processing (NLP) approaches to summarizing, simplifying, and generating patents' text.  ...  Extractive summarization Extractive approaches select the most informative sentences in the original document. A typical pipeline comprises the following steps: 1.  ... 
arXiv:2104.14860v1 fatcat:nc3v6wyimzcblkmdu2da37isiu

Methods of Russian Patent Analysis [chapter]

Dmitriy Korobkin, Sergey Vasiliev, Sergey Fomenkov, S.G. Kolesnikov
2020 Statistical Methodologies  
A new method for extracting structured data from patents has been proposed taking into account the specificity of the text of patents and is based on the shallow parsing and segmentation of sentences.  ...  The extracted structures are converted into a domain ontology and used in prior art patent search and information support of automated invention.  ...  The data source was the main claim of the device from the patent text. And the object of extraction was the SAO semantic structures.  ... 
doi:10.5772/intechopen.90136 fatcat:z7uwynmql5ae7dw3x5e6bpcwfy

Analyzing Parallelism and Domain Similarities in the MAREC Patent Corpus [chapter]

Katharina Wäschle, Stefan Riezler
2012 Lecture Notes in Computer Science  
We document a twofold approach for extracting parallel data from all patent document sections from a large multilingual patent corpus.  ...  Product of our research is a corpus of 23 million parallel German-English sentences extracted from the MAREC patent corpus and a descriptive analysis of its subdomains. 5 http://www.ir-facility.org/prototypes  ...  Acknowledgements The authors would like to thank the Information Retrieval Facility (IRF) for providing the MAREC patent corpus.  ... 
doi:10.1007/978-3-642-31274-8_2 fatcat:orz4rjwt2vaa3lwqrgedtjobg4

Efficient Neural-based patent document segmentation with Term Order Probabilities

Danilo Silva de Carvalho, Minh-Le Nguyen
2017 The European Symposium on Artificial Neural Networks  
The internationally growing trend of patent applications puts great pressure on the agents involved in managing this kind of information and creates a demand for efficient and effective patent analysis  ...  The conducted experiments indicate effectiveness of the approach, which benefits a wide array of patent processing techniques that work upon structured inputs.  ...  This method was developed to facilitate the extraction of structural information from sentences and the generation of sentence embeddings in larger corpora, which are difficult to process using more complex  ... 
dblp:conf/esann/CarvalhoN17 fatcat:wg2fje6yofbipo22oyxmzlhxnm

An Ontology-based Multi-agent Platform for Patent Knowledge Management

Shih-Yao Yang, Szu-Yin Lin, Shih-Neng Lin, Shian-Luen Cheng, Von-Wun Soo
2005 International Journal of Electronic Business Management  
It helps industrial knowledge managers to retrieve and analyze existing patent documents and extract tacit knowledge from patent documents with the aid of ontology and natural language processing techniques  ...  We propose a cooperative Multi-agent knowledge management system to manage patent documents and support the invention process based on the patent document analysis.  ...  The Information Extraction Agent currently only extracts structural relations between objects described in the patent claims.  ... 
dblp:journals/ijebm/YangLLCS05 fatcat:d25hd4k42vdvfhnlqwasxbdrwm

TREC Chemical IR Track 2009: A Distributed Dimensional Indexing Model for Chemical Patent Search

Jay Urbain, Ophir Frieder
2009 Text Retrieval Conference  
The indexing model supports named entity identification and aggregation of term statistics at multiple levels of patent structure including individual words, sentences, claims, descriptions, abstracts,  ...  Query processing for prior art search automatically generates a structured query based on the relative distinctiveness of individual terms and candidate entity phrases from the query patent's claims, abstract  ...  The model supports chemical named entity identification and aggregation of term statistics at multiple levels of patent structure including individual words, sentences, claims, descriptions, abstracts,  ... 
dblp:conf/trec/UrbainF09 fatcat:3rbsyjoxy5eg3esjbw62jk5fxq

SAO2Vec: Development of an algorithm for embedding the subject–action–object (SAO) structure using Doc2Vec

Sunhye Kim, Inchae Park, Byungun Yoon, Diego Raphael Amancio
2020 PLoS ONE  
First, the technical documents of interest are collected, and SAO structures are extracted from them.  ...  Then, sentence vectors are extracted through the Doc2Vec algorithm and are updated using word vectors in the SAO structure.  ...  As an example, the SAO structure from Sentence 218 of the fourth patent in Table 3 is one of the claims related to that patent.  ... 
doi:10.1371/journal.pone.0227930 pmid:32023289 pmcid:PMC7001927 fatcat:ansrtmva4nh5pmj4apyyktkp6a

Using the Diff Command in Patent Documents

Masaki Murata, Hitoshi Isahara
2002 NTCIR Conference on Evaluation of Information Access Technologies  
One is to extract rewriting rules. The second is to align the claims in a patent to the contents of the patent. The third is to extract differences of claims in a patent.  ...  These results would be useful for reading and writing patents.  ...  In this contest, we made the following two kinds of experiments for extraction of rewriting rules from patents. Extraction of rewriting rules by comparing a claim of a patent and its embodiment. 2.  ... 
dblp:conf/ntcir/MurataI02 fatcat:f5wqa6rj6ndn5n4eugbptocpeu

AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis

Junyoung Son, Hyeonseok Moon, Jeongwoo Lee, Seolhwa Lee, Chanjun Park, Wonkyung Jung, Heuiseok Lim
2022 IEEE Access  
The framework comprises two stages: key-sentence extraction and key-phrase generation tasks.  ...  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.  ...  of a patent document from the other sentences and extract them.  ... 
doi:10.1109/access.2022.3176877 fatcat:eb4wjx5r7fepvgg3zj4tmxww5q

Patent Document Summarization Using Conceptual Graphs

Pattabhi R K Rao, Sobha Lalitha Devi
2017 International Journal on Natural Language Computing  
Thus in the present work shallow parsing, NER and machine learning technique for extracting concepts and conceptual relationships from sentences in the claim section of patent documents is used.  ...  It is observed that the general in-depth parsers available in the open domain fail to parse the 'claims section' sentences in patent documents.  ...  We make use of Information Extraction (IE) techniques to cull out the novelty/claim part of the patent document.  ... 
doi:10.5121/ijnlc.2017.6302 fatcat:4qbedlvfjbcbvinhktrsiszlwy
« Previous Showing results 1 — 15 out of 10,774 results