Sentence Representation Learning (SRL) is a fundamental task in Natural
...
Building upon Randomized Discretization, we develop two novel adversaria...
Data augmentation is widely used in text classification, especially in t...
Few-shot text classification has recently been promoted by the meta-lear...
Mixup, which creates synthetic training instances by linearly interpolat...
Opinion target extraction (OTE) or aspect extraction (AE) is a fundament...
We present a variety of novel information-theoretic generalization bound...
Stochastic differential equations (SDEs) have been shown recently to wel...
This paper uses information-theoretic tools to analyze the generalizatio...
Few-shot relation classification (RC) is one of the critical problems in...
Contrastive learning has achieved remarkable success in representation
l...
We present a simple and yet effective interpolation-based regularization...
This paper follows up on a recent work of (Neu, 2021) and presents new a...
Recent researches have suggested that the predictive accuracy of neural
...
The attention mechanism has been widely used in deep neural networks as ...
Recent research has suggested that when training neural networks, flat l...
The dependencies between system and user utterances in the same turn and...
Dialogue state tracking (DST) is an important part of a spoken dialogue
...
SkipGram word embedding models with negative sampling, or SGN in short, ...
Named entity recognition (NER) and Relation extraction (RE) are two
fund...
We consider the problem of learning a neural network classifier. Under t...
Distant supervision for relation extraction enables one to effectively
a...
In this work, we explain the working mechanism of MixUp in terms of
adve...
Mixup, a recent proposed data augmentation method through linearly
inter...
In this paper, we propose a test, called Flagged-1-Bit (F1B) test, to st...
MixUp, a data augmentation approach through mixing random samples, has b...
We establish an equivalence between information bottleneck (IB) learning...
Based on a recent development in the area of error control coding, we
in...