Chia-Hui Chang


2023

pdf bib
Story Co-telling Dialogue Generation via Reinforcement Learning and Knowledge Graph
Yu-Kai Lee | Chia-Hui Chang
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf
Construction of Message Deliver Service Dialog Systems
Cheng-Hung Yeh | Chia-Hui Chang
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
Story Co-telling Dialogue Generation based on Multi-Agent Reinforcement Learning and Story Highlights
Yu-Kai Lee | Chia-Hui Chang
Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association

Retelling a story is one way to develop narrative skills in students, but it may present some challenges for English as Second Language (ESL) students who are learning new stories and vocabularies at the same time. The goal of this research is to develop a dialogue module for story co-telling for ESL students in order to help students to co-narrate an English story and enhance their narrative skills. However, story co-telling is a relatively underexplored and novel task. In order to understand the story content and select the right plot to continue the story co-telling based on the current dialogue, we utilize open domain information extraction techniques to construct a knowledge graph, and adopt multi-agent reinforcement learning methods to train two agents to select relevant facts from the knowledge graph and generate responses, jointly accomplishing the task of story co-telling. Compared to models that reply on chronological order, our model improves the performance from 67.0% to 70.8% through self-training with reward evaluation, achieving an increase of approximately 3.8%.

2022

pdf bib
Question-Answer Pairing from IM Conversations via Message Merging and Reply-to Prediction
Thamolwan Poopradubsil | Chia-Hui Chang
Proceedings of the 36th Pacific Asia Conference on Language, Information and Computation

pdf
Chat-log Disentanglement via Same-Thread Classification and Direct-Reply Prediction
Chia-Hui Chang | Zhi-Xian Liu | Thamolwan Poopradubsil | Yu-Ching Liao | Yu-Hao Wu
Proceedings of the 36th Pacific Asia Conference on Language, Information and Computation

pdf
Applying Information Extraction to Storybook Question and Answer Generation
Kai-Yen Kao | Chia-Hui Chang
Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)

For educators, how to generate high quality question-answer pairs from story text is a time-consuming and labor-intensive task. The purpose is not to make students unable to answer, but to ensure that students understand the story text through the generated question-answer pairs. In this paper, we improve the FairyTaleQA question generation method by incorporating question type and its definition to the input for fine-tuning the BART (Lewis et al., 2020) model. Furthermore, we make use of the entity and relation extraction from (Zhong and Chen, 2021) as an element of template-based question generation.

pdf
Improving Response Diversity through Commonsense-Aware Empathetic Response Generation
Tzu-Hsien Huang | Chia-Hui Chang
Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)

Due to the lack of conversation practice, the main challenge for the second-language learners is speaking. Our goal is to develop a chatbot to encourage individuals to reflect, describe, analyse and communicate what they read as well as improve students’ English expression skills. In this paper, we exploit COMMET, an inferential commonsense knowledge generator, as the background knowledge to improve the generation diversity. We consider two approaches to increase the diversity of empathetic response generation. For nonpretrained models, We apply AdaLabel (Wang et al., 2021) to Commonsense-aware Empathetic model (Sabour et al., 2022) and improve Distinct-2 score from 2.99 to 4.08 on EMPATHETIC DIALOGUES (ED). Furthermore, we augment the pretrained BART model with various commonsense knowledge to generate more informative empathetic responses. Not only has the automatic evaluation of distinct-2 scores improved from 9.11 to 11.21, but the manual case study also shows that CE-BART significantly outperform CEM-AdaLabel.

2021

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 1, June 2021
Chia-Hui Chang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 1, June 2021

pdf bib
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)
Lung-Hao Lee | Chia-Hui Chang | Kuan-Yu Chen
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

pdf
Home Appliance Review Research Via Adversarial Reptile
Tai-Jung Kan | Chia-Hui Chang | Hsiu-Min Chuang
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

For manufacturers of home appliances, the Studying discussion of products on social media can help manufacturers improve their products. Opinions provided through online reviews can immediately reflect whether the product is accepted by people, and which aspect of the product are most discussed . In this article, we divide the analysis of home appliances into three tasks, including named entity recognition (NER), aspect category extraction (ACE), and aspect category sentiment classification (ACSC). To improve the performance of ACSC, we combine the Reptile algorithm in meta learning with the concept of domain adversarial training to form the concept of the Adversarial Reptile algorithm. We find show that the macro-f1 is improved from 68.6% (BERT fine tuned model) to 70.3% (p-value 0.04).

pdf
Aspect-Based Sentiment Analysis and Singer Name Entity Recognition using Parameter Generation Network Based Transfer Learning
Hsiao-Wen Tseng | Chia-Hui Chang | Hsiu-Min Chuang
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

When we are interested in a certain domain, we can collect and analyze data from the Internet. The newly collected data is not labeled, so the use of labeled data is hoped to be helpful to the new data. We perform name entity recognition (NER) and aspect-based sentiment analysis (ABSA) in multi-task learning, and combine parameter generation network and DANN architecture to build the model. In the NER task, the data is labeled with Tie, Break, and the task weight is adjusted according to the loss change rate of each task using Dynamic Weight Average (DWA). This study used two different source domain data sets. The experimental results show that Tie, Break can improve the results of the model; DWA can have better performance in the results; the combination of parameter generation network and gradient reversal layer can be used for every good learning in different domain.

2020

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 25, Number 1, June 2020
Chia-Hui Chang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 25, Number 1, June 2020

pdf
A Hierarchical Decomposable Attention Model for News Stance Detection
Chen-Yu Huang | Chia-Hui Chang
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

pdf
Aspect-Based Sentiment Analysis Based on BERT-DAOA
Chen-Yu Chen | Chia-Hui Chang
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

2019

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 24, Number 1, June 2019
Jen-Tzung Chien | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 24, Number 1, June 2019

pdf bib
應用記憶增強條件隨機場域與之深度學習及自動化詞彙特徵於中文命名實體辨識之研究 (Leveraging Memory Enhanced Conditional Random Fields with Gated CNN and Automatic BAPS Features for Chinese Named Entity Recognition)
Kuo-Chun Chien | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 24, Number 1, June 2019

pdf
基於訊息回應配對相似度估計的聊天記錄解構 (Chatlog Disentanglement based on Similarity Evaluation Via Reply Message Pairs Prediction Task)
ZhiXian Liu | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 24, Number 2, December 2019

pdf
利用Attentive來改善端對端中文語篇剖析遞迴類神經網路系統(Using Attentive to improve Recursive LSTM End-to-End Chinese Discourse Parsing)
Yu-Jen Wang | Chia-Hui Chang
Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019)

pdf
基於訊息配對相似度估計的聊天記錄解構(Chat Log Disentanglement based on Message Pair Similarity Estimation)
ZhiXian Liu | Chia-Hui Chang
Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019)

2018

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 23, Number 1, June 2018
Jen-Tzung Chien | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 23, Number 1, June 2018

2017

pdf
應用興趣點辨識技術從 Web 中挖掘新商家資訊 (Mining POIs from Web via POI recognition and Relation Verification) [In Chinese]
Kuo-Hsin Hsu | Hsiu-Min Chuang | Chien-Lung Chou | Chia-Hui Chang
Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)

pdf
PTT 網站餐廳美食類別擷取之研究 (A Study of Restaurant Information and Food Type Extraction from PTT) [In Chinese]
Chih-Yu Chung | Chien-Lung Chou | Chia-Hui Chang
Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)

2016

pdf
Facebook 活動事件擷取系統(Facebook Activity Event Extraction System)[In Chinese]
Yuan-Hao Lin | Chia-Hui Chang
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

2015

pdf
基於已知名稱搜尋結果的網路實體辨識模型建立工具(A Tool for Web NER Model Generation Using Search Snippets of Known Entities) [In Chinese]
Ya-Yun Huang | Chia-Hui Chang | Chien-Lung Chou
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf
基於Web之商家景點擷取與資料庫建置(Points of Interest Extraction from Unstructured Web)[In Chinese]
Ting-Yao Kao | Hsiu-Min Chuang | Chia-Hui Chang
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

2014

pdf bib
Proceedings of the 26th Conference on Computational Linguistics and Speech Processing (ROCLING 2014)
Jing-Yang Jou | Chia-Hui Chang | Hsin-Min Wang
Proceedings of the 26th Conference on Computational Linguistics and Speech Processing (ROCLING 2014)

pdf
利用核依賴估計來進行多軌自動混音 (Automatic Multi-track Mixing by Kernel Dependency Estimation)[In Chinese]
Tsung Ting Wu | Chia-Hui Chang
Proceedings of the 26th Conference on Computational Linguistics and Speech Processing (ROCLING 2014)

pdf
網頁商家名稱擷取與地址配對之研究 (Store Name Extraction and Name-Address Matching on the Web) [In Chinese]
Yu-Yang Lin | Chia-Hui Chang
Proceedings of the 26th Conference on Computational Linguistics and Speech Processing (ROCLING 2014)

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 19, Number 4, December 2014 - Special Issue on Selected Papers from ROCLING XXVI
Jen-Tzung Chien | Hung-Yu Kao | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 19, Number 4, December 2014 - Special Issue on Selected Papers from ROCLING XXVI

pdf bib
POI 擷取:商家名稱辨識與地址配對之研究 (POI Extraction from the Web: Store Name Recognition and Address Matching) [In Chinese]
Lin Yu-Yang | Chia-Hui Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 19, Number 4, December 2014 - Special Issue on Selected Papers from ROCLING XXVI

pdf
Semi-supervised Sequence Labeling for Named Entity Extraction based on Tri-Training: Case Study on Chinese Person Name Extraction
Chien-Lung Chou | Chia-Hui Chang | Shin-Yi Wu
Proceedings of the Third Workshop on Semantic Web and Information Extraction

2013

pdf
主要漢字形聲字發音規則探勘與視覺化 (Primary Chinese Semantic-Phonetic Compounds Pronunciation Rules Mining and Visualization) [In Chinese]
Chien-Hui Hsu | Meng-Feng Tsai | Chia-Hui Chang | Hsiang-Mei Liao | Shu-Ping Li | Denise H. Wu
Proceedings of the 25th Conference on Computational Linguistics and Speech Processing (ROCLING 2013)

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 18, Number 4, December 2013-Special Issue on Selected Papers from ROCLING XXV
Chia-Hui Chang | Chia-Ping Chen | Jia-Ching Wang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 18, Number 4, December 2013-Special Issue on Selected Papers from ROCLING XXV

2012

pdf
以聲符部件為主之漢字學習系統設計研究 (The Design of Chinese Character Learning System Based on Phonetic Components) [In Chinese]
Chia-Hui Chang | Wen-Pen Wu
Proceedings of the 24th Conference on Computational Linguistics and Speech Processing (ROCLING 2012)

pdf bib
聲符部件排序與形聲字發音規則探勘 (Phonetic Component Ranking and Pronunciation Rules Discovery for Picto-Phonetic Chinese Characters) [In Chinese]
Chia-Hui Chang | Shu-Yen Lin | Meng-Feng Tsai | Shu-Ping Li | Hsiang-Mei Liao | Norden E. Huang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 17, Number 3, September 2012

2011

pdf
聲符部件排序與形聲字發音規則探勘 (Pronunciation Rules Discovery for Picto-Phonetic Chinese Characters) [In Chinese]
Chia-Hui Chang | Shu-Yen Lin
Proceedings of the 23rd Conference on Computational Linguistics and Speech Processing (ROCLING 2011)

2010

pdf
以最佳化及機率分佈判斷漢字聲符之研究 (Automatic Identification of Phonetic Complements for Chinese Characters Based on Optimization and Probability Distribution) [In Chinese]
Chia-Hui Chang | Shu-Ying Li | Sean Lin | Chia-Yi Huang | Jhih-ming Chen
Proceedings of the 22nd Conference on Computational Linguistics and Speech Processing (ROCLING 2010)

pdf
以最佳化及機率分佈標記形聲字聲符之研究 (Annotating Phonetic Component of Chinese Characters Using Constrained Optimization and Pronunciation Distribution) [In Chinese]
Chia-Hui Chang | Shu-Yen Lin | Shu-Ying Li | Meng-Feng Tsai | Shu-Ping Li | Hsiang-Mei Liao | Chih-Wen Sun | Norden E. Huang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 15, Number 2, June 2010

pdf bib
結合長詞優先與序列標記之中文斷詞研究 (A Simple and Effective Closed Test for Chinese Word Segmentation Based on Sequence Labeling) [In Chinese]
Qian-Xiang Lin | Chia-Hui Chang | Chen-Ling Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 15, Number 3-4, September/December 2010

2006

pdf
基於字詞內容之適應性對話系統 (MAGEN: An Adaptive Conversational System based on Terms) [In Chinese]
Yu-De Chu | Chia-Hui Chang
Proceedings of the 18th Conference on Computational Linguistics and Speech Processing

pdf
基於特製隱藏式馬可夫模型之中文斷詞研究 (Chinese Word Segmentation using Specialized HMM) [In Chinese]
Qian-Xiang Lin | Chia-Hui Chang
Proceedings of the 18th Conference on Computational Linguistics and Speech Processing