Устойчивость модели

AbstractZero-shot slot filling has widely arisen to cope with data scarcity in target domains. However, previous approaches often ignore constraints between slot value representation and related slot description representation in …...

AbstractFrame-based state representation is widely used in modern task-oriented dialog systems to model user intentions and slot values. However, a fixed design of domain ontology makes it difficult to extend …...

AbstractDeep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors. Existing explanation methods usually pick …...

AbstractDespite recent progress, state-of-the-art question answering models remain vulnerable to a variety of adversarial attacks. While dynamic adversarial data collection, in which a human annotator tries to write examples that …...

AbstractWe address the problem of enhancing model robustness through regularization. Specifically, we focus on methods that regularize the model posterior difference between clean and noisy inputs. Theoretically, we provide a …...

AbstractRecently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely …...

AbstractCounterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited to promoting core features of the construct over spurious artifacts that happen …...

AbstractNeural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserve the source-side meaning …...

AbstractIn this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation (NMT). We focus on studying the impact of the jointly …...

AbstractNatural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks – malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. …...