There is an increasing interest in continuous learning (CL), as data privacy is becoming a priority for real-world machine learning applications. Meanwhile, there is still a lack of academic NLP benchmarks that are applicable for realistic CL setting
s, which is a major challenge for the advancement of the field. In this paper we discuss some of the unrealistic data characteristics of public datasets, study the challenges of realistic single-task continuous learning as well as the effectiveness of data rehearsal as a way to mitigate accuracy loss. We construct a CL NER dataset from an existing publicly available dataset and release it along with the code to the research community.
Counterfactuals are a valuable means for understanding decisions made by ML systems. However, the counterfactuals generated by the methods currently available for natural language text are either unrealistic or introduce imperceptible changes. We pro
pose CounterfactualGAN: a method that combines a conditional GAN and the embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks. Experimental results show that our method produces perceptibly distinguishable counterfactuals, while outperforming four baseline methods on fidelity and human judgments of naturalness, across multiple datasets and multiple predictive models.
When a model attribution technique highlights a particular part of the input, a user might understand this highlight as making a statement about counterfactuals (Miller, 2019): if that part of the input were to change, the model's prediction might ch
ange as well. This paper investigates how well different attribution techniques align with this assumption on realistic counterfactuals in the case of reading comprehension (RC). RC is a particularly challenging test case, as token-level attributions that have been extensively studied in other NLP tasks such as sentiment analysis are less suitable to represent the reasoning that RC models perform. We construct counterfactual sets for three different RC settings, and through heuristics that can connect attribution methods' outputs to high-level model behavior, we can evaluate how useful different attribution methods and even different formats are for understanding counterfactuals. We find that pairwise attributions are better suited to RC than token-level attributions across these different RC settings, with our best performance coming from a modification that we propose to an existing pairwise attribution method.
In recent years, few-shot models have been applied successfully to a variety of NLP tasks. Han et al. (2018) introduced a few-shot learning framework for relation classification, and since then, several models have surpassed human performance on this
task, leading to the impression that few-shot relation classification is solved. In this paper we take a deeper look at the efficacy of strong few-shot classification models in the more common relation extraction setting, and show that typical few-shot evaluation metrics obscure a wide variability in performance across relations. In particular, we find that state of the art few-shot relation classification models overly rely on entity type information, and propose modifications to the training routine to encourage models to better discriminate between relations involving similar entity types.
