Skip to main navigation Skip to search Skip to main content

CCL23-Eval任务7赛道一系统报告:Suda &Alibaba 文本纠错系统

Translated title of the contribution: CCL23-Eval Task 7 Track 1 System Report: Suda &Alibaba Team Text Error Correction System
  • Haochen Jiang*
  • , Yumeng Liu
  • , Houquan Zhou
  • , Ziheng Qiao
  • , Bo Zhang
  • , Chen Li
  • , Zhenghua Li*
  • , Min Zhang
  • *Corresponding author for this work
  • Soochow University
  • Alibaba Group Holding Ltd.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The article describes the submission of Suda &Alibaba Error Correction Team for Track 1 of the Multidimensional Chinese Learner Text Correction (CCL2023) evaluation task. In terms of models, we used both sequence-to-sequence and sequence-to-edit correction models. For data, we conducted a three-stage training using pseudo data constructed based on confusion sets, real data from Lang-8, and the development set from YACLC. In the open task, we also utilized additional data such as HSK and CGED for training. We employed a series of effective performance enhancement techniques, including rule-based data augmentation, data cleaning, post-processing, and model ensembling. Moreover, we explored the use of large models such as GPT3.5 and GPT4 to assist Chinese text correction and tried various prompts. In both the closed and open tasks, our team ranked first in minimum edits, fluency improvement, and average F0.5 scores.

Translated title of the contributionCCL23-Eval Task 7 Track 1 System Report: Suda &Alibaba Team Text Error Correction System
Original languageChinese (Traditional)
Title of host publicationEvaluations
EditorsMaosong Sun, Bing Qin, Xipeng Qiu, Jing Jiang, Xianpei Han
PublisherAssociation for Computational Linguistics (ACL)
Pages220-229
Number of pages10
ISBN (Electronic)9781713889908
StatePublished - 2023
Externally publishedYes
Event22nd Chinese National Conference on Computational Linguistics, CCL 2023 - Harbin, China
Duration: 3 Aug 20235 Aug 2023

Publication series

NameProceedings of the 22nd Chinese National Conference on Computational Linguistics, CCL 2023
Volume3

Conference

Conference22nd Chinese National Conference on Computational Linguistics, CCL 2023
Country/TerritoryChina
CityHarbin
Period3/08/235/08/23

Fingerprint

Dive into the research topics of 'CCL23-Eval Task 7 Track 1 System Report: Suda &Alibaba Team Text Error Correction System'. Together they form a unique fingerprint.

Cite this