Related papers: Regularization, Semi-supervision, and Supervision …
Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier's decision. We use this framework to…
There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of…
Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such…
The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-components of data. We propose to study the interpretability of…
Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicators. However, in this paper, we find one critical limitation…
Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…
The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…
Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is…
The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have emerged about the…
Human visual system can selectively attend to parts of a scene for quick perception, a biological mechanism known as Human attention. Inspired by this, recent deep learning models encode attention mechanisms to focus on the most…
Attention-based methods have played important roles in model interpretations, where the calculated attention weights are expected to highlight the critical parts of inputs~(e.g., keywords in sentences). However, recent research found that…
The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse…
We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy…
Human explanations of natural language, rationales, form a tool to assess whether models learn a label for the right reasons or rely on dataset-specific shortcuts. Sufficiency is a common metric for estimating the informativeness of…
Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the…
Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translation, in the task of…
The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying…
In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn. This paper proposes a perturbation-based self-supervised attention approach to guide…
Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the…