e Financial Entity Identi cation and Information Integration (FEIII) task aims at the question of understanding relationships among nancial entities and their roles using three sentences extracted from each nancial contract containing the target word. FEIII task has two challenges -1) data sparseness: small training sets (9% of test data) and 2) context sparseness: limited context (three sentences). Existing statistical approaches, such as Bayes and TF-IDF, cannot evaluate the imporatance of

more »

... ds unobservged in training data, which is vulnerable to the above challenges. We overcome each challenge by considering 1) the concepts of words from knowledge bases (Probase) in addition to the words themselves (conceptual feature) and 2) word semantics from distributed representations such as word2vec (semantic feature). We empirically evaluate the proposed classi cation model on the four-class classi cation (highly relevant, relevant, neutral, and irrelevant), and show that the proposed model increases 18% of F1-score compared to the statistical baselines.