Hallucinations in text generation occur when the system produces text th...
Knowing exactly how many data points need to be labeled to achieve a cer...
Large-scale language models, like ChatGPT, have garnered significant med...
Disagreement in natural language annotation has mostly been studied from...
Current work on image-based story generation suffers from the fact that ...
In noisy environments, speech can be hard to understand for humans. Spok...
We propose a shared task on training instance selection for few-shot neu...
Listening in noisy environments can be difficult even for individuals wi...
In this paper, we aim to address the challenges surrounding the translat...
Large-scale pretrained language models have led to dramatic improvements...
For many new application domains for data-to-text generation, the main
o...
Recent advancements in data-to-text generation largely take on the form ...
Neural natural language generation (NLG) and understanding (NLU) models ...
For mixed-initiative control between cyber-physical systems (CPS) and it...
We present a lightweight annotation tool, the Data AnnotatoR Tool (DART)...
West African Pidgin English is a language that is significantly spoken i...
Implicit discourse relation classification is one of the most difficult ...
Implicit discourse relation classification is one of the most challengin...
Variational encoder-decoders (VEDs) have shown promising results in dial...
Discourse-annotated corpora are an important resource for the community....
Recent research in psycholinguistics has provided increasing evidence th...
Inferring implicit discourse relations in natural language text is the m...