No abstract

No abstract

No abstract

Argumentation mining is a research field which focuses on sentences in type of argumentation. Argumentative sentences are often used in daily communication and have important role in each decision or conclusion making process. The research objective is to do observation in deep learning utilization combined with attention mechanism for argument annotation and analysis. Argument annotation is argument component classification from certain discourse to several classes. Classes include major claim, claim, premise and non-argumentative. Argument analysis points to argumentation characteristics and validity which are arranged into one topic. One of the analysis is about how to assess whether an established argument is categorized as sufficient or not. Dataset used for argument annotation and analysis is 402 persuasive essays. This data is translated into Bahasa Indonesia (mother tongue of Indonesia) to give overview about how it works with specific language other than English. Several deep learning models such as CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory), and GRU (Gated Recurrent Unit) are utilized for argument annotation and analysis while HAN (Hierarchical Attention Network) is utilized only for argument analysis. Attention mechanism is combined with the model as weighted access setter for a better performance. From the whole experiments, combination of deep learning and attention mechanism for argument annotation and analysis arrives in a better result compared with previous research.

The goal of this research is to generate a motion-aware claim using a deep neural network approach: sequence-to-sequence learning method. A motion-aware claim is a sentence that is logically correlated to the motion while preserving its grammatical structure. Our proposed model generates a motion-aware claim in a form of one sentence and takes motion as the input also in a form of one sentence. We use a publicly available argumentation mining dataset that contains annotated motion and claim data. In this research, we propose a novel approach for argument generation by employing a scheduled sampling strategy to make the model converge faster. The BLEU scores and questionnaire are used to quantitatively assess the model. Our best model achieves 0.175 ± 0.088 BLEU-4 score. Based on the questionnaire results, we can also derive a conclusion that it is hard for the respondents to differentiate between the human-made and the model-generated arguments.