The deployment of large-scale generative models is often restricted by t...
Through in-context learning (ICL), large-scale language models are effec...
Task-oriented dialogue (TOD) systems are mainly based on the
slot-fillin...
Recent studies have proposed unified user modeling frameworks that lever...
Remembering important information from the past and continuing to talk a...
While Transformers have had significant success in paragraph generation,...
Despite recent explosion in research interests, in-context learning and ...
Text-to-image generation and image captioning are recently emerged as a ...
The retriever-reader pipeline has shown promising performance in open-do...
Recent open-domain dialogue models have brought numerous breakthroughs.
...
Many recent studies on large-scale language models have reported success...
Language models (LMs) have shown great potential as implicit knowledge b...
Pre-trained language models (PLM) have marked a huge leap in neural dial...
Metadata attributes (e.g., user and product IDs from reviews) can be
inc...
GPT-3 shows remarkable in-context learning ability of large-scale langua...
In multi-hop QA, answering complex questions entails iterative document
...
We propose NeuralWOZ, a novel dialogue collection framework that uses
mo...
Large-scale language models such as GPT-3 are excellent few-shot learner...
Language model pre-training has shown promising results in various downs...
Tracking suspected cases of COVID-19 is crucial to suppressing the sprea...
Automatic speech recognition (ASR) via call is essential for various
app...
Recent works in dialogue state tracking (DST) focus on an open
vocabular...
Answerer in Questioner's Mind (AQM) is an information-theoretic framewor...
Goal-oriented dialogue has been paid attention for its numerous applicat...
Deep neural networks continue to advance the state-of-the-art of image
r...