An emerging solution for explaining Transformer-based models is to use
v...
Several proposals have been put forward in recent years for improving
ou...
Parameter-efficient fine-tuning approaches have recently garnered a lot ...
Current pre-trained language models rely on large datasets for achieving...
It has been shown that NLI models are usually biased with respect to the...
There has been a growing interest in interpreting the underlying dynamic...
Several studies have investigated the reasons behind the effectiveness o...
Pre-trained language models have shown stellar performance in various
do...
Several studies have explored various advantages of multilingual pre-tra...
Most of the recent works on probing representations have focused on BERT...
It is widely accepted that fine-tuning pre-trained language models usual...
Existing techniques for mitigating dataset bias often leverage a biased ...
The representation degeneration problem in Contextual Word Representatio...
Several studies have been carried out on revealing linguistic features
c...
The ability to correctly model distinct meanings of a word is crucial fo...
Transformer-based language models have taken many fields in NLP by storm...
We present a new challenging stance detection dataset, called
Will-They-...
In this paper, we present WiC-TSV (Target Sense Verification for
Words i...
Variational Autoencoders (VAEs) are known to suffer from learning
uninfo...
We present a novel method for mapping unrestricted text to knowledge gra...
Word embedding techniques heavily rely on the abundance of training data...
Empirical methods in geoparsing have thus far lacked a standard evaluati...
Rare word representation has recently enjoyed a surge of interest, owing...
By design, word embeddings are unable to model the dynamic nature of wor...
This paper addresses the problem of mapping natural language text to
kno...
Incorporating linguistic, world and common sense knowledge into AI/NLP
s...
Lexical ambiguity can impede NLP systems from accurate understanding of
...
We propose a methodology that adapts graph embedding techniques (DeepWal...
In this paper we investigate the impact of simple text preprocessing
dec...
One major deficiency of most semantic representation techniques is that ...
Representing the semantics of linguistic items in a machine-interpretabl...