Abstract: Relation words arc of great significance for analyzing the semantic relations between clauses in multiple compound sentences. But in the process of automatic identification of relation words based on rule,we found that not all the relation marks in multiple compound sentence arc relation words, and identifying the relation marks serving as relation words is the key point. An algorithm was proposed to identify typical relation words which are adjacent. I3y combining the relationship marked corpus and the extraction of relation markers, this algorithm uses the feature to identify these markers. Experiments prove that this approach achieves the accuracy of 72. 9 0 0 in the identification of these relation marks.

Key words: Marked compound sentence, Adjoining feature, Auto-markup, Rule