---
title: "Chinese Live-Streaming E-Commerce Morph Resolution:"
description: "In Chinese live-stream shopping, hosts often disguise words, for example by inserting fillers or swapping in similar-sounding… 28 references."
authors: ["Jipeng Qiang", "Jiahao Zhu", "Yi Zhu", "Chaowei Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.126/"
doi: "10.18653/v1/2026.findings-acl.126"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/qiang-2026-chinese-live-streaming-e-commerce/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qiang-2026-chinese-live-streaming-e-commerce/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/) / Chinese Live-Streaming E-Commerce Morph Resolution: Datasets and Methods

# Chinese Live-Streaming E-Commerce Morph Resolution: Datasets and Methods

**Authors:** [Jipeng Qiang](https://md.research.elamur.ai/free/en/authors/jipeng-qiang/), Jiahao Zhu, [Yi Zhu](https://md.research.elamur.ai/free/en/authors/yi-zhu/) and [Chaowei Zhang](https://md.research.elamur.ai/free/en/authors/chaowei-zhang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.126/) · [PDF](https://aclanthology.org/2026.findings-acl.126.pdf) · [DOI 10.18653/v1/2026.findings-acl.126](https://doi.org/10.18653/v1/2026.findings-acl.126) · [OpenAlex](https://openalex.org/W7166884703)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
In Chinese live-stream shopping, hosts often disguise words, for example by inserting fillers or swapping in similar-sounding forms. They do this to get past real-time audio moderation and make claims that would otherwise be prohibited. The paper targets recovering the original wording from ASR transcripts, a task the authors call Live Auditory Morph Resolution (LiveAMR).

The only earlier corpus covered health streams alone and was highly repetitive. The authors deduplicated and re-annotated it to produce HealthAMR. They also built GeneralAMR, a new multi-platform, multi-category benchmark that was double-annotated.

On the modelling side, JointMRE trains a model to correct morphs and also output structured explanations as (morph, morph type, original word) triplets, using knowledge distilled from LLMs. A second stage, CDRF, then uses a single LLM call to detect and arbitrate disagreements between the correction and its explanation, applying only targeted edits.

Both stages improve over strong PLM and LLM baselines, and the approach also transfers to Vietnamese normalization. This makes the work relevant to automated regulatory monitoring of e-commerce streams.

## Key points
- **GeneralAMR:** 2,752 one-minute clips from 77 channels on Douyin, Kuaishou and Jingdong, spanning 7 product categories. It contains 28,041 sentences (3,092 with morphs, 24,949 without), covering 567 base words and 1,309 variants. Transcripts come from FunASR's Paraformer, with extra test sets transcribed by Kaldi and Whisper.
- **HealthAMR:** the earlier corpus (7,812 clips from 25 channels) after two cleanup steps. Automatic deduplication removed 22,404 duplicates, and a manual audit added 932 previously missed positive cases. Together the two datasets exceed 92K instances.
- **Reported gains:** JointMRE raises sentence-level F0.5 by 1.93–3.12 points over baselines, and CDRF adds a further 2.8–5.8 points.
- **CDRF configuration and results:** CDRF uses GPT-4.1-mini as its arbitrator, and swapping in other LLMs changes results only marginally. Applied to Llama3.1 outputs, it outperforms Direct Answer, CoT and CoT+RAG prompting. It reaches 88.57 C-F0.5 / 94.65 S-F0.5 on HealthAMR and 88.13 / 92.87 on GeneralAMR.
- **Cross-lingual test:** the method generalizes to the Vietnamese ViLexNorm dataset. Data and code are released on GitHub.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Yangzhou University](https://md.research.elamur.ai/free/en/universities/yangzhou-university/) — University, Yangzhou, China · 2 works · 31 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: Jipeng Qiang, Jiahao Zhu, Yi Zhu and Chaowei Zhang. 2026. Chinese Live-Streaming E-Commerce Morph Resolution: Datasets and Methods. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{qiang2026chinese,
  title = {{Chinese Live-Streaming E-Commerce Morph Resolution: Datasets and Methods}},
  author = {Jipeng Qiang, Jiahao Zhu, Yi Zhu and Chaowei Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.126},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.126}
}
```

- [← previous Chinese Court Simulation with LLM-Based Agents System](https://md.research.elamur.ai/free/en/papers/zhang-2026-chinese-court-simulation-llm-based/)
- [next → ChineseDevBench: A Chinese Developmental Benchmark for Language Development](https://md.research.elamur.ai/free/en/papers/wang-2026-chinesedevbench-chinese-developmental-benchmark-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

28 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ron Artstein. 2017. Inter-annotator agreement. Handbook of linguistic annotation, pages 297–313. [find](https://scholar.google.com/scholar?q=Ron+Artstein%2E+2017%2E+Inter%2Dannotator+agreement%2E+Handbook+of+linguistic+annotation%2C+pages+297%E2%80%93313%2E)
2. Timothy Baldwin, Marie-Catherine De Marneffe, Bo Han, Young-Bum Kim, Alan Ritter, and Wei Xu. 2015. [Shared tasks of the 2015 workshop on noisy user-generated text: Twitter lexical normalization and named entity recognition](https://md.research.elamur.ai/free/en/papers/baldwin-2015-shared-tasks-2015-workshop-noisy/). In Proceedings of the workshop on noisy user-generated text, pages 126–135.
3. Andrey Bout, Alexander Podolskiy, Sergey Nikolenko, and Irina Piontkovskaya. 2023. Efficient grammatical error correction via multi-task training and optimized training schedule. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5800–5816. [find](https://scholar.google.com/scholar?q=Andrey+Bout%2C+Alexander+Podolskiy%2C+Sergey+Nikolenko%2C+and+Irina+Piontkovskaya%2E+2023%2E+Efficient+grammatical+error+correction+via+multi%2Dtask+training+and+optimized+training+schedule%2E+In+Proceedings+of+the)
4. CINI Center. 2022. The 50th statistical report on china’s internet development. Beijing2022. [find](https://scholar.google.com/scholar?q=CINI+Center%2E+2022%2E+The+50th+statistical+report+on+china%E2%80%99s+internet+development%2E+Beijing2022%2E)
5. Jacob Eisenstein. 2013. [What to do about bad language on the internet](https://md.research.elamur.ai/free/en/papers/eisenstein-2013-what-do-about-bad-language/). In Proceedings of the 2013 conference of the North American Chapter of the association for computational linguistics: Human language technologies, pages 359–369.
6. Zhifu Gao, Zerui Li, Jiaming Wang, Haoneng Luo, Xian Shi, Mengzhe Chen, Yabin Li, Lingyun Zuo, Zhihao Du, Zhangyu Xiao, and Shiliang Zhang. 2023. Funasr: A fundamental end-to-end speech recognition toolkit. In INTERSPEECH. [find](https://scholar.google.com/scholar?q=Zhifu+Gao%2C+Zerui+Li%2C+Jiaming+Wang%2C+Haoneng+Luo%2C+Xian+Shi%2C+Mengzhe+Chen%2C+Yabin+Li%2C+Lingyun+Zuo%2C+Zhihao+Du%2C+Zhangyu+Xiao%2C+and+Shiliang+Zhang%2E+2023%2E+Funasr%3A+A+fundamental+end%2Dto%2Dend+speech+recognition+to)
7. Zhifu Gao, Shiliang Zhang, Ian McLoughlin, and Zhijie Yan. 2022. Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. [find](https://scholar.google.com/scholar?q=Zhifu+Gao%2C+Shiliang+Zhang%2C+Ian+McLoughlin%2C+and+Zhijie+Yan%2E+2022%2E+Paraformer%3A+Fast+and+accurate+parallel+transformer+for+non%2Dautoregressive+end%2Dto%2Dend+speech+recognition%2E)
8. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
9. Paul Hsiung, Andrew Moore, Daniel Neill, and Jeff Schneider. 2005. Alias detection in link data sets. In Proceedings of the International Conference on Intelligence Analysis, volume 4. [find](https://scholar.google.com/scholar?q=Paul+Hsiung%2C+Andrew+Moore%2C+Daniel+Neill%2C+and+Jeff+Schneider%2E+2005%2E+Alias+detection+in+link+data+sets%2E+In+Proceedings+of+the+International+Conference+on+Intelligence+Analysis%2C+volume+4%2E)
10. Hongzhao Huang, Zhen Wen, Dian Yu, Heng Ji, Yizhou Sun, Jiawei Han, and He Li. 2013. Resolving entity morphs in censored data. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1083– 1093. [find](https://scholar.google.com/scholar?q=Hongzhao+Huang%2C+Zhen+Wen%2C+Dian+Yu%2C+Heng+Ji%2C+Yizhou+Sun%2C+Jiawei+Han%2C+and+He+Li%2E+2013%2E+Resolving+entity+morphs+in+censored+data%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computat)
11. Ihmily. 2025. Douyinliverecorder: A simple live broadcast recording tool with loopable monitoring. [https://github.com/ihmily/DouyinLiveRecorder](https://github.com/ihmily/DouyinLiveRecorder). [↗](https://github.com/ihmily/DouyinLiveRecorder)
12. Armand Joulin, Edouard Grave, and Piotr Bojanowski Tomas Mikolov. 2017. Bag of tricks for efficient text classification. [find](https://scholar.google.com/scholar?q=Armand+Joulin%2C+Edouard+Grave%2C+and+Piotr+Bojanowski+Tomas+Mikolov%2E+2017%2E+Bag+of+tricks+for+efficient+text+classification%2E)
13. Yinghui Li, Shang Qin, Jingheng Ye, Haojing Huang, Yangning Li, Shu-Yu Guo, Libo Qin, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, and Philip S. Yu. 2025. Rethinking the roles of large language models in Chinese grammatical error correction. In Proceedings of the 63rd Annual Meeting of the Association fo… [find](https://scholar.google.com/scholar?q=Yinghui+Li%2C+Shang+Qin%2C+Jingheng+Ye%2C+Haojing+Huang%2C+Yangning+Li%2C+Shu%2DYu+Guo%2C+Libo+Qin%2C+Xuming+Hu%2C+Wenhao+Jiang%2C+Hai%2DTao+Zheng%2C+and+Philip+S%2E+Yu%2E+2025%2E+Rethinking+the+roles+of+large+language+models+in+C)
14. Ismini Lourentzou, Kabir Manghnani, and ChengXiang Zhai. 2019. Adapting sequence to sequence models for text normalization in social media. In Proceedings of the international AAAI conference on web and social media, volume 13, pages 335–345. [find](https://scholar.google.com/scholar?q=Ismini+Lourentzou%2C+Kabir+Manghnani%2C+and+ChengXiang+Zhai%2E+2019%2E+Adapting+sequence+to+sequence+models+for+text+normalization+in+social+media%2E+In+Proceedings+of+the+international+AAAI+conference+on+web+a)
15. R. Thomas McCoy, Ellie Pavlick, and Tal Linzen. 2019. [Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference](https://md.research.elamur.ai/free/en/papers/mccoy-2019-right-wrong-reasons-diagnosing-syntactic/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3428–3448, Florence, Italy. Association for Computationa…
16. Benjamin Muller, Benoit Sagot, and Djamé Seddah. 2019. Enhancing bert for lexical normalization. In The 5th workshop on noisy user-generated text (W-NUT). [find](https://scholar.google.com/scholar?q=Benjamin+Muller%2C+Benoit+Sagot%2C+and+Djam%C3%A9+Seddah%2E+2019%2E+Enhancing+bert+for+lexical+normalization%2E+In+The+5th+workshop+on+noisy+user%2Dgenerated+text+%28W%2DNUT%29%2E)
17. Canwen Xu, Wangchunshu Zhou, Tao Ge, Ke Xu, Julian McAuley, and Furu Wei. 2021. Blow the dog whistle: A chinese dataset for cant understanding with common sense and world knowledge. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:… [find](https://scholar.google.com/scholar?q=Canwen+Xu%2C+Wangchunshu+Zhou%2C+Tao+Ge%2C+Ke+Xu%2C+Julian+McAuley%2C+and+Furu+Wei%2E+2021%2E+Blow+the+dog+whistle%3A+A+chinese+dataset+for+cant+understanding+with+common+sense+and+world+knowledge%2E+In+Proceedings+of+)
18. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, and 1 others. 2024. Qwen2. 5 technical report. arXiv e-prints, pages arXiv–2412. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+and+1+others%2E+2024%2E+Qwen2%2E+5+technical+report%2E+arXiv+e%2Dprints%2C+pages+arXiv%E2%80%93241)
19. Jirong You, Ying Sha, Qi Liang, and Bin Wang. 2018. Morph resolution based on autoencoders combined with effective context information. In Computational Science–ICCS 2018: 18th International Conference, Wuxi, China, June 11–13, 2018 Proceedings, Part III 18, pages 487–498. Springer. [find](https://scholar.google.com/scholar?q=Jirong+You%2C+Ying+Sha%2C+Qi+Liang%2C+and+Bin+Wang%2E+2018%2E+Morph+resolution+based+on+autoencoders+combined+with+effective+context+information%2E+In+Computational+Science%E2%80%93ICCS+2018%3A+18th+International+Conferenc)
20. Boliang Zhang, Hongzhao Huang, Xiaoman Pan, Heng Ji, Kevin Knight, Zhen Wen, Yizhou Sun, Jiawei Han, and Bulent Yener. 2014. Be appropriate and funny: Automatic entity morph encoding. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers),… [find](https://scholar.google.com/scholar?q=Boliang+Zhang%2C+Hongzhao+Huang%2C+Xiaoman+Pan%2C+Heng+Ji%2C+Kevin+Knight%2C+Zhen+Wen%2C+Yizhou+Sun%2C+Jiawei+Han%2C+and+Bulent+Yener%2E+2014%2E+Be+appropriate+and+funny%3A+Automatic+entity+morph+encoding%2E+In+Proceedings+o)
21. Thanh-Nhi Nguyen, Thanh-Phong Le, and Kiet Nguyen. 2024. Vilexnorm: a lexical normalization corpus for vietnamese social media text. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1421–1437. [find](https://scholar.google.com/scholar?q=Thanh%2DNhi+Nguyen%2C+Thanh%2DPhong+Le%2C+and+Kiet+Nguyen%2E+2024%2E+Vilexnorm%3A+a+lexical+normalization+corpus+for+vietnamese+social+media+text%2E+In+Proceedings+of+the+18th+Conference+of+the+European+Chapter+of+th)
22. Zhuosheng Zhang, Hanqing Zhang, Keming Chen, Yuhang Guo, Jingyun Hua, Yulong Wang, and Ming Zhou. 2021. Mengzi: Towards lightweight yet ingenious pre-trained models for chinese. arXiv preprint arXiv:2110.06696. — [arXiv:2110.06696](https://arxiv.org/abs/2110.06696) [find](https://scholar.google.com/scholar?q=Zhuosheng+Zhang%2C+Hanqing+Zhang%2C+Keming+Chen%2C+Yuhang+Guo%2C+Jingyun+Hua%2C+Yulong+Wang%2C+and+Ming+Zhou%2E+2021%2E+Mengzi%3A+Towards+lightweight+yet+ingenious+pre%2Dtrained+models+for+chinese%2E+arXiv+preprint+arXiv%3A2)
23. Patrick Pantel. 2006. Alias detection in malicious environments. In AAAI Fall Symposium: Capturing and Using Patterns for Evidence Detection, pages 14–20. [find](https://scholar.google.com/scholar?q=Patrick+Pantel%2E+2006%2E+Alias+detection+in+malicious+environments%2E+In+AAAI+Fall+Symposium%3A+Capturing+and+Using+Patterns+for+Evidence+Detection%2C+pages+14%E2%80%9320%2E)
24. Jiahao Zhu, Jipeng Qiang, Ran Bai, Chenyu Liu, and Xiaoye Ouyang. 2025. Chinese morph resolution in E-commerce live streaming scenarios. In NAACL(Volume 3: Industry Track), pages 380–389. [find](https://scholar.google.com/scholar?q=Jiahao+Zhu%2C+Jipeng+Qiang%2C+Ran+Bai%2C+Chenyu+Liu%2C+and+Xiaoye+Ouyang%2E+2025%2E+Chinese+morph+resolution+in+E%2Dcommerce+live+streaming+scenarios%2E+In+NAACL%28Volume+3%3A+Industry+Track%29%2C+pages+380%E2%80%93389%2E)
25. Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, and Samuel R. Bowman. 2020. [Intermediate-task transfer learning with pretrained language models: When and why does it work?](https://md.research.elamur.ai/free/en/papers/pruksachatkun-2020-intermediate-task-transfer-learning-pretrained/) In Proceedings of the 58th Annual Meeting of the Ass…
26. David Samuel and Milan Straka. 2021. \\’ufal at multilexnorm 2021: Improving multilingual lexical normalization by fine-tuning byt5. arXiv preprint arXiv:2110.15248. [find](https://scholar.google.com/scholar?q=David+Samuel+and+Milan+Straka%2E+2021%2E+%5C%5C%E2%80%99ufal+at+multilexnorm+2021%3A+Improving+multilingual+lexical+normalization+by+fine%2Dtuning+byt5%2E+arXiv+preprint+arXiv%3A2110%2E15248%2E)
27. Rob van der Goot. 2019. MoNoise: A multi-lingual and easy-to-use lexical normalization tool. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 201–206, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rob+van+der+Goot%2E+2019%2E+MoNoise%3A+A+multi%2Dlingual+and+easy%2Dto%2Duse+lexical+normalization+tool%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+System+Demonstr)
28. Nannan Wang, Cheng Huang, Junren Chen, and Lingzi Li. 2024. Cmright: Chinese morph resolution based on end-to-end model combined with enhancement algorithms. Expert Systems with Applications, 254:124294. [find](https://scholar.google.com/scholar?q=Nannan+Wang%2C+Cheng+Huang%2C+Junren+Chen%2C+and+Lingzi+Li%2E+2024%2E+Cmright%3A+Chinese+morph+resolution+based+on+end%2Dto%2Dend+model+combined+with+enhancement+algorithms%2E+Expert+Systems+with+Applications%2C+254%3A1242)

*Updated 1 November 2026*