Lift: Language-interfaced fine-tuning for non-language machine learning tasks
Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …
has become a norm for learning various language downstream tasks. However, for non …
" Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking
While communicating with a user, a task-oriented dialogue system has to track the user's
needs at each turn according to the conversation history. This process called dialogue state …
needs at each turn according to the conversation history. This process called dialogue state …
Multi2WOZ: A robust multilingual dataset and conversational pretraining for task-oriented dialog
Research on (multi-domain) task-oriented dialog (TOD) has predominantly focused on the
English language, primarily due to the shortage of robust TOD datasets in other languages …
English language, primarily due to the shortage of robust TOD datasets in other languages …
Multi3NLU++: A multilingual, multi-intent, multi-domain dataset for natural language understanding in task-oriented dialogue
Task-oriented dialogue (TOD) systems have been widely deployed in many industries as
they deliver more efficient customer support. These systems are typically constructed for a …
they deliver more efficient customer support. These systems are typically constructed for a …
Knowing What to Say: Towards knowledge grounded code-mixed response generation for open-domain conversations
Inculcating knowledge in the dialogue agents is an important step towards creating any
agent more human-like. Hence, the use of knowledge while conversing is crucial for building …
agent more human-like. Hence, the use of knowledge while conversing is crucial for building …
X-RiSAWOZ: High-quality end-to-end multilingual dialogue datasets and few-shot agents
Task-oriented dialogue research has mainly focused on a few popular languages like
English and Chinese, due to the high dataset creation cost for a new language. To reduce …
English and Chinese, due to the high dataset creation cost for a new language. To reduce …
Zero-shot language extension for dialogue state tracking via pre-trained models and multi-auxiliary-tasks fine-tuning
Dialogue state tracking (DST), a crucial component of the task-oriented dialogue system
(TOD), is designed to track the user's goal. Existing DST models mainly focus on …
(TOD), is designed to track the user's goal. Existing DST models mainly focus on …
Natural language processing for multilingual task-oriented dialogue
Recent advances in deep learning have also enabled fast progress in the research of task-
oriented dialogue (ToD) systems. However, the majority of ToD systems are developed for …
oriented dialogue (ToD) systems. However, the majority of ToD systems are developed for …
XQA-DST: Multi-domain and multi-lingual dialogue state tracking
Dialogue State Tracking (DST), a crucial component of task-oriented dialogue (ToD)
systems, keeps track of all important information pertaining to dialogue history: filling slots …
systems, keeps track of all important information pertaining to dialogue history: filling slots …
Leveraging natural supervision for language representation learning and generation
M Chen - arXiv preprint arXiv:2207.10617, 2022 - arxiv.org
Recent breakthroughs in Natural Language Processing (NLP) have been driven by
language models trained on a massive amount of plain text. While powerful, deriving …
language models trained on a massive amount of plain text. While powerful, deriving …