Combining Word-Level and Character-Level Representations for Relation Classification of Informal Text

Word representation models have achieved great success in natural language processing tasks, such as relation classification. However, it does not always work on informal text, and the morphemes of some misspelling words may carry important shortdistance semantic information. We propose a hybrid model, combining the merits of word-level and character-level representations to learn better representations on informal text. Experiments on two dataset of relation classification, SemEval2010 Task8 and a large-scale one we compile from informal text, show that our model achieves a competitive result in the former and state-of-the-art with the other.