Search Results for author: Shih-Hung Wu

Found 16 papers, 0 papers with code

基於Seq2Seq模型的中文文法錯誤診斷系統(A Chinese Grammatical Error Diagnosis System Based on Seq2Seq Model)

no code implementations • ROCLING 2019 • Jun-Wei Wang, Sheng-Lun Chien, Yi-Kun Chen, Shih-Hung Wu

Paper
Add Code

CYUT at ROCLING-2021 Shared Task: Based on BERT and MacBERT

no code implementations • ROCLING 2021 • Xie-Sheng Hong, Shih-Hung Wu

This paper present a description for the ROCLING 2021 shared task in dimensional sentiment analysis for educational texts.

regression Sentiment Analysis

Paper
Add Code

CYUT Team Chinese Grammatical Error Diagnosis System Report in NLPTEA-2020 CGED Shared Task

no code implementations • AACL (NLP-TEA) 2020 • Shih-Hung Wu, JunWei Wang

This paper reports our Chinese Grammatical Error Diagnosis system in the NLPTEA-2020 CGED shared task.

Paper
Add Code

Learning the Human Judgment for the Automatic Evaluation of Chatbot

no code implementations • LREC 2020 • Shih-Hung Wu, Sheng-Lun Chien

We believe that it is easier to get consistent results on comparing two generated dialogue by two systems and it is hard to give a consistent quality score on only one system at a time.

Chatbot Dialogue Evaluation

Paper
Add Code

CYUT-III Team Chinese Grammatical Error Diagnosis System Report in NLPTEA-2018 CGED Shared Task

no code implementations • WS 2018 • Shih-Hung Wu, Jun-Wei Wang, Liang-Pu Chen, Ping-Che Yang

This paper reports how we build a Chinese Grammatical Error Diagnosis system in the NLPTEA-2018 CGED shared task.

Language Modelling

Paper
Add Code

A Short Answer Grading System in Chinese by Support Vector Approach

no code implementations • WS 2018 • Shih-Hung Wu, Wen-Feng Shih

In this paper, we report a short answer grading system in Chinese.

BIG-bench Machine Learning Semantic Textual Similarity

Paper
Add Code

CYUT at IJCNLP-2017 Task 3: System Report for Review Opinion Diversification

no code implementations • IJCNLP 2017 • Shih-Hung Wu, Su-Yu Chang, Liang-Pu Chen

Review Opinion Diversification (RevOpiD) 2017 is a shared task which is held in International Joint Conference on Natural Language Processing (IJCNLP).

regression