37 citations · 64 across the 15 of their papers we have counts for
16 papers
Miutsu: NTU's TaskBot for the Alexa Prize
Yen-Ting Lin, Hui-Chi Kuo, Ze-Song Xu +5
This paper introduces Miutsu, National Taiwan University's Alexa Prize TaskBot, which is designed to assist users in completing tasks requiring multiple steps and decisions in two…
Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems
Po-Nien Kung, Chung-Cheng Chang, Tse-Hsuan Yang +3
Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and…
Relating Neural Text Degeneration to Exposure Bias
Ting-Rui Chiang, Yun-Nung Chen
This work focuses on relating two mysteries in neural-based text generation: exposure bias, and text degeneration. Despite the long time since exposure bias was mentioned and the n…
Modeling Diagnostic Label Correlation for Automatic ICD Coding
Shang-Chi Tsai, Chao-Wei Huang, Yun-Nung Chen
Given the clinical notes written in electronic health records (EHRs), it is challenging to predict the diagnostic codes which is formulated as a multi-label classification task. Th…
Mitigating Biases in Toxic Language Detection through Invariant Rationalization
Yung-Sung Chuang, Mingye Gao, Hongyin Luo +4
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attribute…
Why Can You Lay Off Heads? Investigating How BERT Heads Transfer
Ting-Rui Chiang, Yun-Nung Chen
The huge size of the widely used BERT family models has led to recent efforts about model distillation. The main goal of distillation is to create a task-agnostic pre-trained model…
Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning
Shengsheng Zhang, Yaping Huang, Yun Chen +3
Most existing Grammatical Error Correction (GEC) methods based on sequence-to-sequence mainly focus on how to generate more pseudo data to obtain better performance. Few work addre…
An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker
Yen-Ting Lin, Yun-Nung Chen
There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets. However, the progress of dialogue systems in low-resource…
TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
Chun-Hsing Lin, Siang-Ruei Wu, Hung-Yi Lee +1
Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems. This is mainly…
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro +36
This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in…
Dual Inference for Improving Language Understanding and Generation
Shang-Yu Su, Yung-Sung Chuang, Yun-Nung Chen
Natural language understanding (NLU) and Natural language generation (NLG) tasks hold a strong dual relationship, where NLU aims at predicting semantic labels based on natural lang…
Toward Cross-Lingual Definition Generation for Language Learners
Cunliang Kong, Liner Yang, Tianzuo Zhang +4
Generating dictionary definitions automatically can prove useful for language learners. However, it's still a challenging task of cross-lingual definition generation. In this work,…
What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding
Yu-An Wang, Yun-Nung Chen
In recent years, pre-trained Transformers have dominated the majority of NLP benchmark tasks. Many variants of pre-trained Transformers have kept breaking out, and most focus on de…
Lifelong Language Knowledge Distillation
Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen
It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts. To addres…
Towards Unsupervised Language Understanding and Generation by Joint Dual Learning
Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen
In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given…
Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification
Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen
Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret…