000048029 000__ 02101cam\a22003375i\4500
000048029 001__ 48029
000048029 005__ 20240708150356.0
000048029 006__ m\\\\eo\\d\\\\\\\\
000048029 008__ 230328s2023\\\\sz\\\\\\\\\\\\000\0\eng\d
000048029 0247_ $$2doi$$a10.1016/j.wpi.2023.102173
000048029 035__ $$a(OCoLC)1284952498
000048029 040__ $$aSzGeWIPO$$beng$$erda$$cSzGeWIPO$$dCaBNVSL
000048029 041__ $$aeng
000048029 24500 $$aEvaluating generative patent language models.
000048029 264_1 $$aOxford [England] :$$bElsevier Ltd.,$$c2023
000048029 300__ $$a1 volume.
000048029 337__ $$aunmediated$$bn$$2rdamedia
000048029 4901_ $$aWorld Patent Information,$$v72, March, 2023.
000048029 520__ $$aGenerative language models are promising for assisting human writing in various domains. This manuscript aims to build generative language models in the patent domain and evaluate model performance from a human-centric perspective. The perspective is to measure the ratio of keystrokes that can be saved by autocompletion based on generative patent language models. A higher ratio means a more effective model which can save more keystrokes. This metric can be used to benchmark model performance. The metric is keystroke-based and different from conventional machine-centric metrics that are token-based. In terms of model size, the largest model built in this manuscript is PatentGPT-J-6B, which is state-of-the-art in the patent domain. Based on the metric, it is found that the largest model is not necessarily the best for the human-centric metric. The finding means that keeping increasing model sizes in the patent domain might be unnecessary if the purpose is to assist human writing with autocompletion. Several patent language models are pre-trained from scratch in this research. The pre-trained models are released for future researchers. Several visualization tools are also provided. The importance of building a generative language model in the patent domain is its potential to facilitate creativity and innovations in the future.
000048029 542__ $$fhttps://www.sciencedirect.com/science/article/pii/S0172219023000030
000048029 588__ $$aCrossref
000048029 590__ $$aPublished online: 30-Jan-23
000048029 650_0 $$aPatents.
000048029 7001_ $$aLee, Jieh-Sheng,$$eauthor.
000048029 7730_ $$tWorld Patent Information$$wWPI
000048029 830_0 $$aWorld Patent Information,$$v72, March, 2023.
000048029 85641 $$uhttps://doi.org/10.1016/j.wpi.2023.102173$$yonline version
000048029 904__ $$aJournal article
000048029 980__ $$aWPI