TueFact at SemEval 2019 Task 8: Fact checking in community question answering forums: context matters
Réka Juhász, Franziska Barbara Linnenschmidt, Teslin Roys · 2019
The SemEval 2019 Task 8 on Fact-Checking in community question answering forums aimed to classify questions into categories and verify the correctness of answers given on the QatarLiving public forum.The task was divided into two subtasks: the first classifying the question, the second the answers.The Tue-Fact system described in this paper used different approaches for the two subtasks.Subtask A makes use of word vectors based on a bagof-word-ngram model using up to trigrams.Predictions are done using multi-class logistic regression.The official SemEval result lists an accuracy of 0.60.Subtask B uses vectorized character n-grams up to trigrams instead.Predictions are done using a LSTM model and achieved an accuracy of 0.53 on the final Se-mEval Task 8 evaluation set.In a comparison of contextual inputs to subtask B, it was determined that more contextual data improved results, but only up to a point.