In the first part of this technical report we describe our approach to design a new data format, based on XML (Extensible Markup Language) and aimed to provide a better and unifying alternative to various legacy data formats used in various areas of corpus linguistics and specifically in the field of structured annotation. We introduce the first version of the format, called Prague Markup Language (PML). This version has already been employed as the main data format for the upcoming Prague Dependency Treebank 2.0 (PDT). Finally we outline our ideas and proposals for further improvement of PML, based on our current experience with using and processing data in PML format in the PDT 2.0 project. The second part of the technical report contains the state-of-the-art specification of PML. Technicka zprava c. TR-2005-29 Technicka zprava projektu Integrace jazykových zdrojů za ucelem extrakce informaci z přirozených textů Projekt Informacni spolecnosti Grantove agentury Akademie věd CR Registracni cislo GA AV CR: 1ET101120503 Interni kod MFF: 207-14 / 242083