Uncertainty in natural language processing: Sources, quantification, and applications
As a main field of artificial intelligence, natural language processing (NLP) has achieved
remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in …
remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in …
Uncertainty quantification with pre-trained language models: A large-scale empirical analysis
Pre-trained language models (PLMs) have gained increasing popularity due to their
compelling prediction performance in diverse natural language processing (NLP) tasks …
compelling prediction performance in diverse natural language processing (NLP) tasks …
Retrieve-and-sample: Document-level event argument extraction via hybrid retrieval augmentation
Y Ren, Y Cao, P Guo, F Fang, W Ma… - Proceedings of the 61st …, 2023 - aclanthology.org
Recent studies have shown the effectiveness of retrieval augmentation in many generative
NLP tasks. These retrieval-augmented methods allow models to explicitly acquire prior …
NLP tasks. These retrieval-augmented methods allow models to explicitly acquire prior …
Learning to generalize to more: Continuous semantic augmentation for neural machine translation
The principal task in supervised neural machine translation (NMT) is to learn to generate
target sentences conditioned on the source inputs from a set of parallel sentence pairs, and …
target sentences conditioned on the source inputs from a set of parallel sentence pairs, and …
Self-training sampling with monolingual data uncertainty for neural machine translation
Self-training has proven effective for improving NMT performance by augmenting model
training with synthetic parallel data. The common practice is to construct synthetic data …
training with synthetic parallel data. The common practice is to construct synthetic data …
Rethinking data augmentation for low-resource neural machine translation: A multi-task learning approach
VM Sánchez-Cartagena, M Esplà-Gomis… - arXiv preprint arXiv …, 2021 - arxiv.org
In the context of neural machine translation, data augmentation (DA) techniques may be
used for generating additional training samples when the available parallel data are scarce …
used for generating additional training samples when the available parallel data are scarce …
Exploring predictive uncertainty and calibration in NLP: A study on the impact of method & data scarcity
We investigate the problem of determining the predictive confidence (or, conversely,
uncertainty) of a neural classifier through the lens of low-resource languages. By training …
uncertainty) of a neural classifier through the lens of low-resource languages. By training …
Confidence-aware scheduled sampling for neural machine translation
Scheduled sampling is an effective method to alleviate the exposure bias problem of neural
machine translation. It simulates the inference scene by randomly replacing ground-truth …
machine translation. It simulates the inference scene by randomly replacing ground-truth …
Unsupervised learning of deterministic dialogue structure with edge-enhanced graph auto-encoder
It is important for task-oriented dialogue systems to discover the dialogue structure (ie the
general dialogue flow) from dialogue corpora automatically. Previous work models dialogue …
general dialogue flow) from dialogue corpora automatically. Previous work models dialogue …
SUN: Exploring intrinsic uncertainties in text-to-SQL parsers
This paper aims to improve the performance of text-to-SQL parsing by exploring the intrinsic
uncertainties in the neural network based approaches (called SUN). From the data …
uncertainties in the neural network based approaches (called SUN). From the data …