Large, pre-trained language models (PLMs) such as BERT and GPT have drastically
changed the Natural Language Processing (NLP) field. For numerous NLP tasks …

In the era of deep learning, modeling for most natural language processing (NLP) tasks has
converged into several mainstream paradigms. For example, we usually adopt the …

Practitioners increasingly use machine learning (ML) models, yet models have become
more complex and harder to understand. To understand complex models, researchers have …

Event extraction (EE) is a crucial information extraction task that aims to extract event
information in texts. Previous methods for EE typically model it as a classification task, which …

Pre-trained language models have been recently shown to benefit task-oriented dialogue
(TOD) systems. Despite their success, existing methods often formulate this task as a …

MultiWOZ 2.0 (Budzianowski et al., 2018) is a recently released multi-domain dialogue
dataset spanning 7 distinct domains and containing over 10,000 dialogues. Though …

The underlying difference of linguistic patterns between general text and task-oriented
dialogue makes existing pre-trained language models less useful in practice. In this work …

In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design
process of task-oriented dialogue systems and alleviate the over-dependency on annotated …

Task-oriented dialog systems rely on dialog state tracking (DST) to monitor the user's goal
during the course of an interaction. Multi-domain and open-vocabulary settings complicate …

Due to the significance and value in human-computer interaction and natural language
processing, task-oriented dialog systems are attracting more and more attention in both …