The STUDIA UNIVERSITATIS BABEŞ-BOLYAI issue article summary

The summary of the selected article appears at the bottom of the page. In order to get back to the contents of the issue this article belongs to you have to access the link from the title. In order to see all the articles of the archive which have as author/co-author one of the authors mentioned below, you have to access the link from the author's name.

INTRODUCTION. The field of Information Extraction (IE) studies and creates techniques for turning the unstructured information present in natural language texts into structured data [7]. An important part of this process is coreference resolution, the task which identifies when different noun phrases refer to the same discourse entity in a text. Coreference resolution is a field which has been extensively researched for English (see [9] for a comprehensive overview of methods), but received less attention for other languages. This is due to the fact that the vast majority of the existing methods are based on machine learning and therefore require extensive annotated data.

Key words and phrases. coreference resolution, parallel corpus, machine learning.