Autoregressive large language models (LLMs) have made remarkable progres...
State-of-the-art few-shot learning (FSL) methods leverage prompt-based
f...
Recent research has focused on enhancing the capability of smaller model...
Generalization to unseen tasks is an important ability for few-shot lear...
Modern Natural Language Generation (NLG) models come with massive
comput...
Standard fine-tuning of large pre-trained language models (PLMs) for
dow...
Neural architecture search (NAS) has demonstrated promising results on
i...
Fine-tuning large-scale pre-trained language models to downstream tasks
...
Traditional multi-task learning (MTL) methods use dense networks that us...
Knowledge distillation (KD) methods compress large models into smaller
s...
Most recent progress in natural language understanding (NLU) has been dr...
Recent works have focused on compressing pre-trained language models (PL...
We present a new method LiST for efficient fine-tuning of large pre-trai...
While pre-trained language models have obtained state-of-the-art perform...
Existing bias mitigation methods for DNN models primarily work on learni...
While deep and large pre-trained models are the state-of-the-art for var...
The combination of multilingual pre-trained representations and cross-li...
State-of-the-art deep neural networks require large-scale labeled traini...
Neural sequence labeling is an important technique employed for many Nat...
Recent success of large-scale pre-trained language models crucially hing...
Email remains one of the most frequently used means of online communicat...
Web search engines are frequently used to access information about produ...
Intelligent features in email service applications aim to increase
produ...
Multilingual representations embed words from many languages into a sing...
Deep and large pre-trained language models are the state-of-the-art for
...
Controversial claims are abundant in online media and discussion forums....
Recent advances in pre-training huge models on large amounts of text thr...
Social influence plays a vital role in shaping a user's behavior in onli...
In this paper, we consider advancing web-scale knowledge extraction and
...
Misinformation such as fake news is one of the big challenges of our soc...
Extraction of missing attribute values is to find values describing an
a...
One of the major hurdles preventing the full exploitation of information...
Online review communities are dynamic as users join and leave, adopt new...
Online reviews provide viewpoints on the strengths and shortcomings of
p...
Media seems to have become more partisan, often providing a biased cover...
Online health communities are a valuable source of information for patie...
Current recommender systems exploit user and item similarities by
collab...
Online reviews provided by consumers are a valuable asset for e-Commerce...