LELIO: An Auto-Adaptative System to Acquire Domain Lexical Knowledge in Technical Texts

LELIO: An Auto-Adaptative System to Acquire Domain Lexical Knowledge in Technical Texts Patrick Saint-Dizier IRIT-CNRS, 118 route de Narbonne, 31062 Toulouse cedex France, stdizier@irit.fr Abstract In this paper, we investigate some language acquisition facets of an auto-adaptative system that can automatically acquire most of the relevant lexical knowledge and authoring practices for an application in a given domain. This is the LELIO project: producing customized LELIE solutions. Our goal, within the framework of LELIE (a system that tags language uses that do not follow the Constrained Natural Language principles), is to automate the long, costly and error prone lexical customization of LELIE to a given application domain. Technical texts being relatively restricted in terms of syntax and lexicon, results obtained show that this approach is feasible and relatively reliable. By auto-adaptative, we mean that the system learns from a sample of the application corpus the various lexical terms and uses crucial for LELIE to work properly (e.g. verb uses, fuzzy terms, business terms, stylistic patterns). A technical writer validation method is developed at each step of the acquisition. Keywords: Lexical Acquisition, Constrained Natural Language, Technical Text Authoring 1. Aims and Challenges Technical documents form a linguistic genre with specific linguistic constraints in terms of lexical realization, syntax, typography and overall document organization, including business or domain dependent aspects. Technical docu- ments cover a large variety of types of documents: pro- cedures, equipment and product manuals, various notices such as security notices, regulations of various types (se- curity, management), requirements and specifications (Hull et ali. 2011). These documents are designed to be easy to read and as efficient and unambiguous as possible for their users. They must leave little space for personal interpreta- tions. For that purpose, they tend to follow relatively strict controlled natural language (CNL hereafter) principles con- cerning both their form and contents (Fuchs 2012), (Kuhn 2014) (Aurora et ali. 2013). These principles are described in documents called authoring guidelines. These are gen- eral purpose statements, norms in e.g. aeronautics, chem- istry, or considerations proper to a company. Guidelines contain some details about e.g. the terms which can be used (for example, a limited subset of verbs) or not and syntactic structures which are allowed or preferred. Stylistic consid- erations may also be introduced, for example concerning the order of complements or subordinate clauses (e.g. con- dition - main clause - purpose). These considerations have motivated the development of the LELIE project (Barcellini et al. 2012), (Saint-Dizier 2014), which is a system that detects several types of errors in technical documents, whatever their authoring and revi- sion stages are. Lelie produces alerts related to these errors on terms, expressions or constructions that need various forms of improvements, at all levels: lexical, syntactic, se- mantics and discourse. LELIE deals with errors which are not detected by usual text editors such as MS Word. These errors may indeed be perfectly acceptable expressions in non-technical language. For each application domain, and for each company, LELIE must be customized. The major part …

Content truncated to 500 words