360 citations · 478 across the 11 of their papers we have counts for
18 papers
Continual Training of Language Models for Few-Shot Learning
Zixuan Ke, Haowei Lin, Yijia Shao +3
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can pr…
Zero-Shot Aspect-Based Sentiment Analysis
Lei Shu, Hu Xu, Bing Liu +1
Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning. It is a big challenge to scale ABSA to a large number of new…
Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
Hu Xu, Lei Shu, Philip S. Yu +1
This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA). Our work is motivated by the recent pro…
A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution
Hu Xu, Bing Liu, Lei Shu +1
Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classif…
Modeling Multi-Action Policy for Task-Oriented Dialogues
Lei Shu, Hu Xu, Bing Liu +1
Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system. In most existing approaches, the agent predicts only o…
Flexibly-Structured Model for Task-Oriented Dialogues
Lei Shu, Piero Molino, Mahdi Namazifar +4
This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, wher…