In Grammatical Error Correction (GEC), it is crucial to ensure the user'...
Discriminatory social biases, including gender biases, have been found i...
Pre-trained language models trained on large-scale data have learned ser...
Despite their impressive performance in a wide range of NLP tasks, Large...
Large Language Models (LLMs) have achieved human-level fluency in text
g...
Large-scale pre-trained language models such as GPT-3 have shown remarka...
Large Language Models (LLMs) have demonstrated remarkable performance in...
Humans work together to solve common problems by having discussions,
exp...
Numerous types of social biases have been identified in pre-trained lang...
We study the relationship between task-agnostic intrinsic and task-speci...
Impressive performance of Transformer has been attributed to self-attent...
Combining multiple source embeddings to create meta-embeddings is consid...
Sense embedding learning methods learn different embeddings for the diff...
Grammatical Error Correction (GEC) should not focus only on high accurac...
This study investigates how supervised quality estimation (QE) models of...
Neural models trained with large amount of parallel data have achieved
i...
Neural machine translation (NMT) has recently gained widespread attentio...
Grammatical error correction (GEC) suffers from a lack of sufficient par...
Masked Language Models (MLMs) have shown superior performances in numero...
Parallel corpora are indispensable for training neural machine translati...
Word embeddings trained on large corpora have shown to encode high level...
In comparison to the numerous debiasing methods proposed for the static
...
Prior work investigating the geometry of pre-trained word embeddings hav...
Existing approaches for grammatical error correction (GEC) largely rely ...
This paper investigates how to effectively incorporate a pre-trained mas...
Simultaneous translation involves translating a sentence before the spea...
Word embeddings learnt from massive text collections have demonstrated
s...
It is known that a deep neural network model pre-trained with large-scal...
This study explores the necessity of performing cross-corpora evaluation...