Multi-Granular Text Encoding for Self-Explaining Categorization

TL;DR: An initial attempt to evaluate explanation methods from an alternative viewpoint and proposes a principled metric based on fidelity in regard to the predictive behavior of the NMT model.

TL;DR: This article investigated various methods to improve the interpretability of deep neural networks for natural language processing (NLP) tasks, including machine translation and sentiment analysis, and provided a comprehensive discussion on the definition of the term ''interpretability'' and its various aspects at the beginning of this work.

TL;DR: The authors proposed a multi-passage Discourse-aware Entailment Reasoning Network (MUDERN), which extracts conditions in the rule texts through discourse segmentation, conducts multipassage entailment reasoning to answer user questions directly, or asks clarification follow-up questions to inquiry more information.

TL;DR: Local interpretations for Explainable NLP models survey local interpretation techniques for improving the interpretability of deep neural networks for NLP tasks.

TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.

TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.

TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.