Experiments show the effectiveness of GMASK in providing faithful explanations to these models. GMASK selects the best materials from Japan to produce screen protectors for all types of gadgets. The proposed method is evaluated with two different model architectures (decomposable attention model and BERT) across four datasets, including natural language inference and paraphrase identification tasks. In this work, we propose the Group Mask (GMASK) method to implicitly detect word correlations by grouping correlated words from the input text pair together and measure their contribution to the corresponding NLP tasks as a whole. However, for models with text pairs as inputs (e.g., paraphrase identification), existing methods are not sufficient to capture feature interactions between two texts and their simple extension of computing all word-pair interactions between two texts is computationally inefficient. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features. Publisher = "Association for Computational Linguistics ",Ībstract = "Explaining neural network models is important for increasing their trustworthiness in real-world applications. Title = "Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks ",Īuthor = "Chen, Hanjie and Feng, Song and Ganhotra, Jatin and Wan, Hui and Gunasekara, Chulaka and Joshi, Sachindra and Ji, Yangfeng ",īooktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ",
0 kommentar(er)
