Jie Mei


2023

pdf bib
Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical Scenarios
Yufan Wang | Jie Mei | Bowei Zou | Rui Fan | Tingting He | Ai Ti Aw
Findings of the Association for Computational Linguistics: ACL 2023

Most previous few-shot Spoken Language Understanding (SLU) models typically need to be trained on a set of data-rich source domains and adapt to the target domain with a few examples. In this paper, we explore a more practical scenario for few-shot SLU, in which we only assume access to a pre-trained language model and a few labeled examples without any other source domain data. We concentrate on understanding how far the few-shot SLU could be pushed in this setting. To this end, we develop a prompt-based intent detection model in few-shot settings, which leverages the BERT original pre-training next sentence prediction task and the prompt template to detect the user’s intent. For slot filling, we propose an approach of reconstructing slot labels, which reduces the training complexity by reducing the number of slot labels in few-shot settings. To evaluate the few-shot SLU for a more practical scenario, we present two benchmarks, FewShotATIS and FewShotSNIPS. And a dynamic sampling strategy is designed to construct the two datasets according to the learning difficulty of each intent and slot. Experiments on FewShotATIS and FewShotSNIPS demonstrate that our proposed model achieves state-of-the-art performance.

2021

pdf bib
MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization
Chenguang Zhu | Yang Liu | Jie Mei | Michael Zeng
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

This paper introduces MediaSum, a large-scale media interview dataset consisting of 463.6K transcripts with abstractive summaries. To create this dataset, we collect interview transcripts from NPR and CNN and employ the overview and topic descriptions as summaries. Compared with existing public corpora for dialogue summarization, our dataset is an order of magnitude larger and contains complex multi-party conversations from multiple domains. We conduct statistical analysis to demonstrate the unique positional bias exhibited in the transcripts of televised and radioed interviews. We also show that MediaSum can be used in transfer learning to improve a model’s performance on other dialogue summarization tasks.

2016

pdf bib
DalGTM at SemEval-2016 Task 1: Importance-Aware Compositional Approach to Short Text Similarity
Jie Mei | Aminul Islam | Evangelos Milios
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)