mhirano at the FinSBD Task: Pointwise Prediction Based on Multi-layer Perceptron for Sentence Boundary Detection

This paper proposes a pointwise prediction for a sentence boundary detection task. The proposed pointwise prediction is combined with our original word embedding method and three-layered perceptron. It predicts whether the targeted words have the role of the beginning/end of a sentence or not by using word features around the targeted words. We tested our model by changing some parameters in our model and then ensembled these models with various parameters. Consequently, the ensembled model achieved 0.88 and 0.84 averaged f1-score by testing the data both in English and French, and it also obtained 0.84 in English and 0.86 in French as the final results of this shared task. In addition, we developed a baseline model, that is, a rule-based prediction model, for comparison. The result shows that the proposed pointwise prediction model outperformed the rule-based prediction model in any index.