The objective of few-shot named entity recognition is to identify named
...
Zero-shot cross-domain slot filling aims to transfer knowledge from the
...
Existing controllable dialogue generation work focuses on the
single-att...
Pre-trained language models based on general text enable huge success in...
Currently, the reduction in the parameter scale of large-scale pre-train...
Generalized intent discovery aims to extend a closed-set in-domain inten...
This paper studies the discovery of approximate rules in property graphs...
With the continuous development of business process management technolog...
Few-shot named entity recognition (NER) aims at identifying named entiti...
In real dialogue scenarios, the existing slot filling model, which tends...
Graph entity dependencies (GEDs) are novel graph constraints, unifying k...
A critical step in sharing semantic content online is to map the structu...
Detecting out-of-domain (OOD) intents from user queries is essential for...
Discovering out-of-domain (OOD) intent is important for developing new s...
Recent advances in neural approaches greatly improve task-oriented dialo...
Detecting Out-of-Domain (OOD) or unknown intents from user queries is
es...
Out-of-Domain (OOD) detection is a key component in a task-oriented dial...
Traditional intent classification models are based on a pre-defined inte...
Dialogue bots have been widely applied in customer service scenarios to
...
Most existing slot filling models tend to memorize inherent patterns of
...
The most advanced abstractive dialogue summarizers lack generalization
a...
Previous dialogue summarization datasets mainly focus on open-domain chi...
Zero-shot cross-domain slot filling alleviates the data dependence in th...
Existing slot filling models can only recognize pre-defined in-domain sl...
Detecting Out-of-Domain (OOD) or unknown intents from user queries is
es...
The bug triaging process, an essential process of assigning bug reports ...
Recent years have witnessed the rapid development of service-oriented
co...
Next (or successive) point-of-interest (POI) recommendation has attracte...