Afficher la notice abrégée

dc.rights.licenseopenen_US
hal.structure.identifierBordeaux Sciences Economiques [BSE]
dc.contributor.authorSTERZI, Valerio
IDREF: 228222427
hal.structure.identifierBordeaux Sciences Economiques [BSE]
dc.contributor.authorASCIONE, G.S.
dc.date.accessioned2024-03-28T15:16:11Z
dc.date.available2024-03-28T15:16:11Z
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/189080
dc.description.abstractEnThe problem of disambiguation of company names poses a significant challenge in extracting useful information from patents. This issue biases research outcomes as it mostly underesti mates the number of patents attributed to companies, particularly multinational corporations which file patents under a plethora of names, including alternate spellings of the same en tity and, eventually, companies’ subsidiaries.To date, addressing these challenges has relied on labor-intensive dictionary based or string matching approaches, leaving the problem of patents’ assignee harmonization on large datasets mostly unresolved. To bridge this gap, this paper describes the Terrorizer algorithm, a text-based algorithm that leverages natural language processing (NLP), network theory, and rule-based techniques to harmonize the vari ants of company names recorded as patent assignees. In particular, the algorithm follows the tripartite structure of its antecedents, namely parsing, matching and filtering stage, adding an original ”knowledge augmentation” phase which is used to enrich the information available on each assignee name. We use Terrorizer on a set of 325’917 companies’ names who are as signees of patents granted by the USPTO from 2005 to 2022. The performance of Terrorizer is evaluated on four gold standard datasets. This validation step shows us two main things: the first is that the performance of Terrorizer is similar over different kind of datasets, prov ing that our algorithm generalizes well. Second, when comparing its performance with the one of the algorithm currently used in PatentsView for the same task (Monath et al., 2021), it achieves a higher F1 score. Finally, we use the Tree-structured Parzen Estimator (TPE) optimization algorithm for the hyperparameters’ tuning. Our final result is a reduction in the initial set of names of over 42%.
dc.language.isoENen_US
dc.rightsAttribution 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/us/*
dc.subject.enEntity linking
dc.subject.enPatent assignee
dc.subject.enNatural language processing
dc.subject.enNetwork theory
dc.title.enPresenting Terrorizer : an algorithm for consolidating company names in patent assignees
dc.typeDocument de travail - Pré-publicationen_US
dc.subject.halSciences de l'Homme et Société/Economies et financesen_US
bordeaux.hal.laboratoriesBordeaux Sciences Economiques / Bordeaux School of Economics (BSE) - UMR 6060en_US
bordeaux.institutionUniversité de Bordeauxen_US
bordeaux.institutionCNRSen_US
bordeaux.institutionINRAEen_US
hal.identifierhal-04525318
hal.version1
hal.date.transferred2024-03-28T15:16:12Z
hal.popularnonen_US
hal.audienceInternationaleen_US
hal.exporttrue
dc.rights.ccCC BYen_US
bordeaux.subtypePrepublication/Preprinten_US
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=STERZI,%20Valerio&ASCIONE,%20G.S.&rft.genre=preprint


Fichier(s) constituant ce document

Thumbnail
Thumbnail

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée