We evaluate a semantic parser based on a character-based sequence-to-sequence model in the context of the SemEval2017 shared task on semantic parsing for AMRs. With data augmentation, super characters, and POS-tagging we gain major improvements in performance compared to a baseline character-level model. Although we improve on previous character-based neural semantic parsing models, the overall...

This paper describes our approach for the Detecting Stance in Tweets task (SemEval-2016 Task 6). We utilized recent advances in short text categorization using deep learning to create word-level and character-level models. The choice between word-level and characterlevel models in each particular case was informed through validation performance. Our final system is a combination of classifiers ...

We show that a character-level encoderdecoder framework can be successfully applied to question answering with a structured knowledge base. We use our model for singlerelation question answering and demonstrate the effectiveness of our approach on the SimpleQuestions dataset (Bordes et al., 2015), where we improve state-of-the-art accuracy from 63.9% to 70.9%, without use of ensembles. Importan...

The performance of any machine learning model largely depends on the type input data provided. higher volume and variety data, better models get trained, thereby producing more accurate results. However, it is a challenging task to high in some cases containing enough variety. Handwritten character recognition for Odia language one them. NITROHCS v1.0 handwritten characters ISI image database n...