Towards an Error Correction Memory to Enhance Technical Texts Authoring in LELIE
This work addresses error correction for technical text authors, but it appears incremental as it builds on existing frameworks without introducing a major breakthrough.
The paper tackles the problem of fuzzy lexical items in technical texts by proposing an error correction memory to induce generic correction patterns and contextual recommendations, resulting in a system that enhances text authoring within the LELIE project.
In this paper, we investigate and experiment the notion of error correction memory applied to error correction in technical texts. The main purpose is to induce relatively generic correction patterns associated with more contextual correction recommendations, based on previously memorized and analyzed corrections. The notion of error correction memory is developed within the framework of the LELIE project and illustrated on the case of fuzzy lexical items, which is a major problem in technical texts.