UTMN at HAHA@IberLEF2019: Recognizing Humor in Spanish Tweets Using Hard Parameter Sharing for Neural Networks.

Automatic humor detection is a hard but challenging task. For the competition HAHA at IberLEF 2019 we built a neural networks classifier that uses different types of neural networks for specific sets of features. After being trained separately, the layers are concatenated to give the general output. The performance of our system on the binary detection of humorous tweets reaches F-score of 0.76 which is comparably higher than results of baseline machine learning classifiers and earns us the ninth place in the ranking table. As for task 2, where the system has to guess how funny the tweet was based on the number of stars that it got, our result is similarly good: RMSE = 0.945. However, much needs to be done to evaluate contribution of each of the feature sets and our choice of the type of neural network.