Résumé
The development of the Terahertz laser technology in quantum cascadelasers (qcl) has brought about great potential for industrial applications. Theselasers are based on the Terahertz electromagnetic waves, in the frequency rangefrom about 100GHz to 10THz. There is need to understand the structure of thelaser and its influence on the performance in order to optimize the design process.One way of collating this information is by having ontologies and knowledge basescapturing the various qcl designs and their performance characteristics. Majority ofthe laser design data is usually contained in scientific literature. The main drawbackof such textual data sources is their unstructured nature. The complex nature of thelaser design and the varying author language styles poses some level of difficulty inretrieving this information. Owing to this, the existing methods needs improvementin order retrieve the laser information at a high precision(with minimal number ofincorrect records extracted) and minimized number of correct records not extracted.In this paper, we tackle this initial challenge by proposing a text mining pipeline formining the qcl properties by extending the grammar rules of a conditional randomfield (CRF) based model using a rule-based approach. The properties of interestinclude: hetero-structure (laser stacking properties), working temperature, lasingfrequency, laser thickness and the optical power. We evaluate the pipeline on sampleopen access journal papers from AIP, OPTICA and IOP Publishers.