OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis
This work addresses customer feedback analysis for multilingual applications, but it is incremental as it applies existing neural methods to a shared task.
The paper tackled multilingual customer feedback analysis by experimenting with simple neural architectures, achieving top-5 performance in Spanish and French tasks with exact-accuracy and micro-average-F1 scores up to 85.28% and 73.17%, respectively.
This paper describes our systems for IJCNLP 2017 Shared Task on Customer Feedback Analysis. We experimented with simple neural architectures that gave competitive performance on certain tasks. This includes shallow CNN and Bi-Directional LSTM architectures with Facebook's Fasttext as a baseline model. Our best performing model was in the Top 5 systems using the Exact-Accuracy and Micro-Average-F1 metrics for the Spanish (85.28% for both) and French (70% and 73.17% respectively) task, and outperformed all the other models on comment (87.28%) and meaningless (51.85%) tags using Micro Average F1 by Tags metric for the French task.