Recent research has shown that multi-task pre-training greatly improves ...
Visually-grounded dialog systems, which integrate multiple modes of
comm...
Training large language models (LLMs) with open-domain instruction data ...
Measuring the quality of responses generated by LLMs is a challenging ta...
Large language models (LLMs) often contain misleading content, emphasizi...
When trying to answer complex questions, people often rely on multiple
s...
Existing multimodal task-oriented dialog data fails to demonstrate the
d...
Perceiving multi-modal information and fulfilling dialogues with humans ...
Large language models (LLMs) have exhibited an emergent in-context learn...
Recently, speech-text pre-training methods have shown remarkable success...
The goal of document-grounded dialogue (DocGD) is to generate a response...
Real-world data often have an open long-tailed distribution, and buildin...
Lifelong learning (LL) is an important ability for NLP models to learn n...
Out-of-Domain (OOD) intent detection is vital for practical dialogue sys...
Out-of-distribution (OOD) detection is essential for the reliable and sa...
Recent research has shown that Large Language Models (LLMs) can utilize
...
Multi-document grounded dialogue systems (DGDS) belong to a class of
con...
Empathetic dialogue is a human-like behavior that requires the perceptio...
Table-based reasoning has shown remarkable progress in combining deep mo...
Existing multimodal conversation agents have shown impressive abilities ...
Open Information Extraction (OpenIE) facilitates the open-domain discove...
Lifelong learning aims to accumulate knowledge and alleviate catastrophi...
Practical dialog systems need to deal with various knowledge sources, no...
Multimodal sentiment analysis (MSA) and emotion recognition in conversat...
Out-of-Domain (OOD) intent detection is important for practical dialog
s...
Text-to-SQL parsing tackles the problem of mapping natural language ques...
In this paper, we propose a novel SQL guided pre-training framework STAR...
This paper introduces Doc2Bot, a novel dataset for building machines tha...
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD...
Most graph-to-text works are built on the encoder-decoder framework with...
Recently, pre-training methods have shown remarkable success in task-ori...
Pre-training methods with contrastive learning objectives have shown
rem...
This paper aims to improve the performance of text-to-SQL parsing by
exp...
Large transformer models display promising performance on a wide range o...
QA models with lifelong learning (LL) abilities are important for practi...
Text-to-SQL parsing is an essential and challenging task. The goal of
te...
Deep learning recommendation models (DLRMs) have been widely applied in
...
Building document-grounded dialogue systems have received growing intere...
The importance of building text-to-SQL parsers which can be applied to n...
As fine-grained visual classification (FGVC) being developed for decades...
In this paper, we present Duplex Conversation, a multi-turn, multimodal
...
A slot value might be provided segment by segment over multiple-turn
int...
The task of converting a natural language question into an executable SQ...
Pre-trained models have proved to be powerful in enhancing task-oriented...
Recently pre-training models have significantly improved the performance...
The Transformer architecture has improved the performance of deep learni...
Existing dialog state tracking (DST) models are trained with dialog data...
Text-to-SQL aims to map natural language questions to SQL queries. The
s...
Semantic parsing has long been a fundamental problem in natural language...
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-sho...