---
title: "Extending Czech Aspect-Based Sentiment Analysis — Šmíd 2026"
description: "Czech aspect-based sentiment analysis (ABSA) has had no data with opinion term labels."
authors: ["Jakub Šmíd", "Pavel Priban", "Pavel Kral"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.633/"
doi: "10.63317/4hkzdnwfztkz"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/smid-2026-extending-czech-aspect-based-sentiment/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/smid-2026-extending-czech-aspect-based-sentiment/)

[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/6/) / Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

# Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

**Authors:** [Jakub Šmíd](https://md.research.elamur.ai/free/en/authors/jakub-smid/), Pavel Priban, [Pavel Kral](https://md.research.elamur.ai/free/en/authors/pavel-kral/) · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.633/) · [PDF](https://aclanthology.org/2026.lrec-1.633.pdf) · [DOI 10.63317/4hkzdnwfztkz](https://doi.org/10.63317/4hkzdnwfztkz) · [OpenAlex](https://openalex.org/W7160068178)

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

## Summary
Czech aspect-based sentiment analysis (ABSA) has had no data with opinion term labels. As a result, tasks that link aspects, categories, opinions and polarity could only be studied in English. The authors extend the existing CsRest-M restaurant review corpus, which already has train, validation and test splits, with opinion term annotations. Their guidelines drew on USAGE, ACOS and ASQP and were refined over several rounds. Unlike most English resources, the opinion spans keep intensity modifiers, and implicit opinions are labelled "NULL". Some original triplets were split, and some polarities were corrected. The resource supports ASTE, ASQP and ACOS. The authors describe it as the first non-English dataset for quadruplet-level ABSA. They benchmark Transformer models and LLMs (zero-shot, few-shot, fine-tuned) in monolingual, multilingual and cross-lingual setups. They also propose an LLM-driven translation and label alignment approach for cross-lingual transfer, which gives consistent gains. Error analysis shows that subtle opinion expressions and nuanced sentiment remain difficult. The method offers a scalable template for other low-resource languages, such as Ukrainian.

## Key points
- **Dataset:** a new Czech restaurant-domain ABSA dataset built on CsRest-M (Šmíd et al., 2024b). It adds opinion terms to the existing (aspect term, category, polarity) triplets. Dataset and code are public on GitHub (biba10/Czech-ABSA-Opinion-Dataset-Benchmark).
- **Tasks covered:** ASTE (a, o, p), plus ASQP and ACOS (a, c, o, p). ACOS additionally allows implicit "NULL" opinion terms.
- **Annotation choices:**
  - Modifiers such as "velmi" (very) are kept inside opinion spans, because they change sentiment intensity in Czech. This departs from the English ASTE/ACOS conventions and complicates cross-lingual comparison.
  - Aspects with mixed sentiment, previously labelled neutral, are split into separate positive and negative quadruplets.
- **Models and settings:** LLMs (e.g., LLaMA 3.1) were tested in zero-shot, few-shot and QLoRA-style fine-tuning setups. They were compared against a multilingual sequence-to-sequence baseline in monolingual, multilingual and cross-lingual settings. The authors say this is the first cross-lingual study covering all three tasks.
- **Cross-lingual transfer:** the proposed method uses LLMs to translate the training data and align its labels, and it consistently improves cross-lingual results.
- **Missing numbers:** concrete benchmark scores are not given here, because the results section was missing from the supplied text.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

Topics: [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/)

## Cite

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

```bibtex
@inproceedings{smid2026extending,
  title = {{Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks}},
  author = {Šmíd, Jakub and Priban, Pavel and Kral, Pavel},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4hkzdnwfztkz},
  url = {https://doi.org/10.63317/4hkzdnwfztkz}
}
```

- [← previous Extending Creativity: Large Language Models and the Practice of Poetry Translation](https://md.research.elamur.ai/free/en/papers/resende-2026-extending-creativity-large-language-models/)
- [next → Extracting First Order Logic formulas from graphical semantic representations](https://md.research.elamur.ai/free/en/papers/vergnette-2026-extracting-first-order-logic-formulas/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

44 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Viraat Aryabumi, John Dang, Dwarak Talupuru, Saurabh Dash, David Cairuz, Hangyu Lin, Bharat Venkitesh, Madeline Smith, Jon Ander Campos, Yi Chern Tan, Kelly Marchisio, Max Bartolo, Sebastian Ruder, Acyr Locatelli, Julia Kreutzer, Nick Frosst, Aidan Gomez, Phil Blunsom, Marzieh Fadaee, Ahmet Üstün, a… [find](https://scholar.google.com/scholar?q=Viraat+Aryabumi%2C+John+Dang%2C+Dwarak+Talupuru%2C+Saurabh+Dash%2C+David+Cairuz%2C+Hangyu+Lin%2C+Bharat+Venkitesh%2C+Madeline+Smith%2C+Jon+Ander+Campos%2C+Yi+Chern+Tan%2C+Kelly+Marchisio%2C+Max+Bartolo%2C+Sebastian+Ruder%2C+Ac) [our card](https://md.research.elamur.ai/free/en/papers/aryabumi-2024-aya-23-open-weight-releases/)
2. Hongjie Cai, Rui Xia, and Jianfei Yu. 2021. Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing… [find](https://scholar.google.com/scholar?q=Hongjie+Cai%2C+Rui+Xia%2C+and+Jianfei+Yu%2E+2021%2E+Aspect%2Dcategory%2Dopinion%2Dsentiment+quadruple+extraction+with+implicit+aspects+and+opinions%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+) [our card](https://md.research.elamur.ai/free/en/papers/cai-2021-aspect-category-opinion-sentiment-quadruple/)
3. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient fine-tuning of quantized llms. In Advances in Neural Information Processing Systems, volume 36, pages 10088–10115. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Tim+Dettmers%2C+Artidoro+Pagnoni%2C+Ari+Holtzman%2C+and+Luke+Zettlemoyer%2E+2023%2E+Qlora%3A+Efficient+fine%2Dtuning+of+quantized+llms%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+36%2C+pages+10088%E2%80%931)
4. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, et al. 2024. The llama 3 herd of models. [find](https://scholar.google.com/scholar?q=Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+et+al%2E+2024%2E+The+llama+3+herd+of+models%2E)
5. Chris Dyer, Victor Chahuneau, and Noah A. Smith. 2013. A simple, fast, and effective reparameterization of IBM model 2. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 644–648, Atlanta, Georgia.… [find](https://scholar.google.com/scholar?q=Chris+Dyer%2C+Victor+Chahuneau%2C+and+Noah+A%2E+Smith%2E+2013%2E+A+simple%2C+fast%2C+and+effective+reparameterization+of+IBM+model+2%2E+In+Proceedings+of+the+2013+Conference+of+the+North+American+Chapter+of+the+Assoc)
6. Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang, and Jiajun Chen. 2019. Target-oriented opinion words extraction with target-fused neural sequence labeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologi… [find](https://scholar.google.com/scholar?q=Zhifang+Fan%2C+Zhen+Wu%2C+Xin%2DYu+Dai%2C+Shujian+Huang%2C+and+Jiajun+Chen%2E+2019%2E+Target%2Doriented+opinion+words+extraction+with+target%2Dfused+neural+sequence+labeling%2E+In+Proceedings+of+the+2019+Conference+of+th)
7. Tianhao Gao, Jun Fang, Hanyu Liu, Zhiyuan Liu, Chao Liu, Pengzhang Liu, Yongjun Bao, and Weipeng Yan. 2022. LEGO-ABSA: A prompt-based task assemblable unified generative framework for multi-task aspect-based sentiment analysis. In Proceedings of the 29th International Conference on Computational Lin… [find](https://scholar.google.com/scholar?q=Tianhao+Gao%2C+Jun+Fang%2C+Hanyu+Liu%2C+Zhiyuan+Liu%2C+Chao+Liu%2C+Pengzhang+Liu%2C+Yongjun+Bao%2C+and+Weipeng+Yan%2E+2022%2E+LEGO%2DABSA%3A+A+prompt%2Dbased+task+assemblable+unified+generative+framework+for+multi%2Dtask+aspec)
8. Zhibin Gou, Qingyan Guo, and Yujiu Yang. 2023. MvP: Multi-view prompting improves aspect sentiment tuple prediction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4380–4397, Toronto, Canada. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Zhibin+Gou%2C+Qingyan+Guo%2C+and+Yujiu+Yang%2E+2023%2E+MvP%3A+Multi%2Dview+prompting+improves+aspect+sentiment+tuple+prediction%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Ling)
9. Tomáš Hercig, Tomáš Brychcín, Lukáš Svoboda, Michal Konkol, and Josef Steinberger. 2016. Unsupervised methods to improve aspect-based sentiment analysis in czech. Computación y Sistemas, 20(3):365–375. [find](https://scholar.google.com/scholar?q=Tom%C3%A1%C5%A1+Hercig%2C+Tom%C3%A1%C5%A1+Brychc%C3%ADn%2C+Luk%C3%A1%C5%A1+Svoboda%2C+Michal+Konkol%2C+and+Josef+Steinberger%2E+2016%2E+Unsupervised+methods+to+improve+aspect%2Dbased+sentiment+analysis+in+czech%2E+Computaci%C3%B3n+y+Sistemas%2C+20%283%29%3A365%E2%80%93375)
10. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Edward+J+Hu%2C+Yelong+Shen%2C+Phillip+Wallis%2C+Zeyuan+Allen%2DZhu%2C+Yuanzhi+Li%2C+Shean+Wang%2C+Lu+Wang%2C+and+Weizhu+Chen%2E+2022%2E+LoRA%3A+Low%2Drank+adaptation+of+large+language+models%2E+In+International+Conference+on+L) [our card](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/)
11. Roman Klinger and Philipp Cimiano. 2014. The USAGE review corpus for fine grained multi lingual opinion analysis. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 2211– 2218, Reykjavik, Iceland. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Roman+Klinger+and+Philipp+Cimiano%2E+2014%2E+The+USAGE+review+corpus+for+fine+grained+multi+lingual+opinion+analysis%2E+In+Proceedings+of+the+Ninth+International+Conference+on+Language+Resources+and+Evaluat)
12. Ladislav Lenc and Tomás Hercig. 2016. Neural networks for sentiment analysis in czech. In Proceedings of the 16th ITAT: Slovenskočeský NLP workshop (SloNLP 2016), volume 1649 of CEUR Workshop Proceedings, pages 48–55, Bratislava, Slovakia. Comenius University in Bratislava, Faculty of Mathematics, P… [find](https://scholar.google.com/scholar?q=Ladislav+Lenc+and+Tom%C3%A1s+Hercig%2E+2016%2E+Neural+networks+for+sentiment+analysis+in+czech%2E+In+Proceedings+of+the+16th+ITAT%3A+Slovensko%C4%8Desk%C3%BD+NLP+workshop+%28SloNLP+2016%29%2C+volume+1649+of+CEUR+Workshop+Proceedi)
13. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2019%2E+Decoupled+weight+decay+regularization%2E)
14. Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, and Longjun Cai. 2022. Seq2Path: Generating sentiment tuples as paths of a tree. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2215–2225, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yue+Mao%2C+Yi+Shen%2C+Jingchao+Yang%2C+Xiaoying+Zhu%2C+and+Longjun+Cai%2E+2022%2E+Seq2Path%3A+Generating+sentiment+tuples+as+paths+of+a+tree%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2022%2C+)
15. Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andres Codas, Clarisse Simoes, Sahaj Agarwal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, and Ahmed Awadallah. 2023. Orca 2: Teaching small language models how to reason. [find](https://scholar.google.com/scholar?q=Arindam+Mitra%2C+Luciano+Del+Corro%2C+Shweti+Mahajan%2C+Andres+Codas%2C+Clarisse+Simoes%2C+Sahaj+Agarwal%2C+Xuxi+Chen%2C+Anastasia+Razdaibiedina%2C+Erik+Jones%2C+Kriti+Aggarwal%2C+Hamid+Palangi%2C+Guoqing+Zheng%2C+Corby+Ross) [our card](https://md.research.elamur.ai/free/en/papers/mitra-2023-orca-2-teaching-small-language/)
16. OpenAI. 2024. GPT-4o. Accessed November 2024. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+GPT%2D4o%2E+Accessed+November+2024%2E)
17. Haiyun Peng, Lu Xu, Lidong Bing, Fei Huang, Wei Lu, and Luo Si. 2020. Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8600–8607. [find](https://scholar.google.com/scholar?q=Haiyun+Peng%2C+Lu+Xu%2C+Lidong+Bing%2C+Fei+Huang%2C+Wei+Lu%2C+and+Luo+Si%2E+2020%2E+Knowing+what%2C+how+and+why%3A+A+near+complete+solution+for+aspect%2Dbased+sentiment+analysis%2E+Proceedings+of+the+AAAI+Conference+on+Art)
18. Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeniy Kotelnikov, Nuria Bel, Salud María Jiménez-Z… [find](https://scholar.google.com/scholar?q=Maria+Pontiki%2C+Dimitris+Galanis%2C+Haris+Papageorgiou%2C+Ion+Androutsopoulos%2C+Suresh+Manandhar%2C+Mohammad+AL%2DSmadi%2C+Mahmoud+Al%2DAyyoub%2C+Yanyan+Zhao%2C+Bing+Qin%2C+Orph%C3%A9e+De+Clercq%2C+V%C3%A9ronique+Hoste%2C+Marianna+Api) [our card](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/)
19. Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Suresh Manandhar, and Ion Androutsopoulos. 2015. SemEval-2015 task 12: Aspect based sentiment analysis. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 486–495, Denver, Colorado. Association for Comput… [find](https://scholar.google.com/scholar?q=Maria+Pontiki%2C+Dimitris+Galanis%2C+Haris+Papageorgiou%2C+Suresh+Manandhar%2C+and+Ion+Androutsopoulos%2E+2015%2E+SemEval%2D2015+task+12%3A+Aspect+based+sentiment+analysis%2E+In+Proceedings+of+the+9th+International+Wor) [our card](https://md.research.elamur.ai/free/en/papers/pontiki-2015-semeval-2015-task-12-aspect/)
20. Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. SemEval-2014 task 4: Aspect based sentiment analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 27–35, Dublin, Ireland. Associa… [find](https://scholar.google.com/scholar?q=Maria+Pontiki%2C+Dimitris+Galanis%2C+John+Pavlopoulos%2C+Harris+Papageorgiou%2C+Ion+Androutsopoulos%2C+and+Suresh+Manandhar%2E+2014%2E+SemEval%2D2014+task+4%3A+Aspect+based+sentiment+analysis%2E+In+Proceedings+of+the+8th) [our card](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/)
21. Pavel Přibáň and Ondřej Pražák. 2023. Improving aspect-based sentiment with end-to-end semantic role labeling model. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 888–897, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria. [find](https://scholar.google.com/scholar?q=Pavel+P%C5%99ib%C3%A1%C5%88+and+Ond%C5%99ej+Pra%C5%BE%C3%A1k%2E+2023%2E+Improving+aspect%2Dbased+sentiment+with+end%2Dto%2Dend+semantic+role+labeling+model%2E+In+Proceedings+of+the+14th+International+Conference+on+Recent+Advances+in+Natural+L)
22. Marzieh Saeidi, Guillaume Bouchard, Maria Liakata, and Sebastian Riedel. 2016. Senti-Hood: Targeted aspect based sentiment analysis dataset for urban neighbourhoods. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1546–1556, Osak… [find](https://scholar.google.com/scholar?q=Marzieh+Saeidi%2C+Guillaume+Bouchard%2C+Maria+Liakata%2C+and+Sebastian+Riedel%2E+2016%2E+Senti%2DHood%3A+Targeted+aspect+based+sentiment+analysis+dataset+for+urban+neighbourhoods%2E+In+Proceedings+of+COLING+2016%2C+the)
23. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
24. Jakub Šmíd and Pavel Kral. 2025. Cross-lingual aspect-based sentiment analysis: A survey on tasks, approaches, and challenges. Information Fusion, 120:103073. [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd+and+Pavel+Kral%2E+2025%2E+Cross%2Dlingual+aspect%2Dbased+sentiment+analysis%3A+A+survey+on+tasks%2C+approaches%2C+and+challenges%2E+Information+Fusion%2C+120%3A103073%2E)
25. Jakub Šmíd and Pavel Přibáň. 2023. Prompt-based approach for Czech sentiment analysis. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 1110–1120, Varna, Bulgaria. IN-COMA Ltd., Shoumen, Bulgaria. [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd+and+Pavel+P%C5%99ib%C3%A1%C5%88%2E+2023%2E+Prompt%2Dbased+approach+for+Czech+sentiment+analysis%2E+In+Proceedings+of+the+14th+International+Conference+on+Recent+Advances+in+Natural+Language+Processing%2C+pages+1110)
26. Jakub Šmíd, Pavel Priban, and Pavel Kral. 2024a. LLaMA-based models for aspect-based sentiment analysis. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 63–70, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd%2C+Pavel+Priban%2C+and+Pavel+Kral%2E+2024a%2E+LLaMA%2Dbased+models+for+aspect%2Dbased+sentiment+analysis%2E+In+Proceedings+of+the+14th+Workshop+on+Computational+Approaches+to+Subjectivity%2C+Sentiment%2C+%26+S)
27. Jakub Šmíd, Pavel Přibáň, and Pavel Kral. 2025a. Advancing cross-lingual aspect-based sentiment analysis with llms and constrained decoding for sequence-to-sequence models. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, pages 757–766. IN… [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd%2C+Pavel+P%C5%99ib%C3%A1%C5%88%2C+and+Pavel+Kral%2E+2025a%2E+Advancing+cross%2Dlingual+aspect%2Dbased+sentiment+analysis+with+llms+and+constrained+decoding+for+sequence%2Dto%2Dsequence+models%2E+In+Proceedings+of+the+17th+)
28. Jakub Šmíd, Pavel Priban, and Pavel Kral. 2025b. LACA: Improving cross-lingual aspect-based sentiment analysis with LLM data augmentation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 839–853, Vienna, Austria. Association f… [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd%2C+Pavel+Priban%2C+and+Pavel+Kral%2E+2025b%2E+LACA%3A+Improving+cross%2Dlingual+aspect%2Dbased+sentiment+analysis+with+LLM+data+augmentation%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+)
29. Jakub Šmíd, Pavel Přibáň, and Pavel Král. 2026. Large language models for czech aspect-based sentiment analysis. In Text, Speech, and Dialogue, pages 15–26, Cham. Springer Nature Switzerland. [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd%2C+Pavel+P%C5%99ib%C3%A1%C5%88%2C+and+Pavel+Kr%C3%A1l%2E+2026%2E+Large+language+models+for+czech+aspect%2Dbased+sentiment+analysis%2E+In+Text%2C+Speech%2C+and+Dialogue%2C+pages+15%E2%80%9326%2C+Cham%2E+Springer+Nature+Switzerland%2E)
30. Jakub Šmíd, Pavel Přibáň, Ondrej Prazak, and Pavel Kral. 2024b. Czech dataset for complex aspect-based sentiment analysis tasks. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4299–4310, Torino, Ital… [find](https://scholar.google.com/scholar?q=Jakub+%C5%A0m%C3%ADd%2C+Pavel+P%C5%99ib%C3%A1%C5%88%2C+Ondrej+Prazak%2C+and+Pavel+Kral%2E+2024b%2E+Czech+dataset+for+complex+aspect%2Dbased+sentiment+analysis+tasks%2E+In+Proceedings+of+the+2024+Joint+International+Conference+on+Computatio)
31. Josef Steinberger, Tomáš Brychcín, and Michal Konkol. 2014. Aspect-level sentiment analysis in Czech. In Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 24–30, Baltimore, Maryland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Josef+Steinberger%2C+Tom%C3%A1%C5%A1+Brychc%C3%ADn%2C+and+Michal+Konkol%2E+2014%2E+Aspect%2Dlevel+sentiment+analysis+in+Czech%2E+In+Proceedings+of+the+5th+Workshop+on+Computational+Approaches+to+Subjectivity%2C+Sentiment+and+Soci)
32. Ales Tamchyna, Ondrej Fiala, and Katerina Veselovská. 2015. Czech aspect-based sentiment analysis: A new dataset and preliminary results. In ITAT, pages 95–99. [find](https://scholar.google.com/scholar?q=Ales+Tamchyna%2C+Ondrej+Fiala%2C+and+Katerina+Veselovsk%C3%A1%2E+2015%2E+Czech+aspect%2Dbased+sentiment+analysis%3A+A+new+dataset+and+preliminary+results%2E+In+ITAT%2C+pages+95%E2%80%9399%2E)
33. Gemma Team, Aishwarya Kamath, et al. 2025. Gemma 3 technical report. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+et+al%2E+2025%2E+Gemma+3+technical+report%2E)
34. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30, page 6000–6010. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N+Gomez%2C+%C5%81+ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+Advances+in+Neural+Information+Process) [our card](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/)
35. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoe… [find](https://scholar.google.com/scholar?q=Thomas+Wolf%2C+Lysandre+Debut%2C+Victor+Sanh%2C+Julien+Chaumond%2C+Clement+Delangue%2C+Anthony+Moi%2C+Pierric+Cistac%2C+Tim+Rault%2C+Remi+Louf%2C+Morgan+Funtowicz%2C+Joe+Davison%2C+Sam+Shleifer%2C+Patrick+von+Platen%2C+Clara+M) [our card](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
36. Chengyan Wu, Bolei Ma, Zheyu Zhang, Ningyuan Deng, Yanqing He, and Yun Xue. 2025. Evaluating zero-shot multilingual aspect-based sentiment analysis with large language models. International Journal of Machine Learning and Cybernetics. [find](https://scholar.google.com/scholar?q=Chengyan+Wu%2C+Bolei+Ma%2C+Zheyu+Zhang%2C+Ningyuan+Deng%2C+Yanqing+He%2C+and+Yun+Xue%2E+2025%2E+Evaluating+zero%2Dshot+multilingual+aspect%2Dbased+sentiment+analysis+with+large+language+models%2E+International+Journal+of)
37. Luo Xianlong, Meng Yang, and Yihao Wang. 2023. Tagging-assisted generation model with encoder and decoder supervision for aspect sentiment triplet extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2078–2093, Singapore. Association for Comput… [find](https://scholar.google.com/scholar?q=Luo+Xianlong%2C+Meng+Yang%2C+and+Yihao+Wang%2E+2023%2E+Tagging%2Dassisted+generation+model+with+encoder+and+decoder+supervision+for+aspect+sentiment+triplet+extraction%2E+In+Proceedings+of+the+2023+Conference+on+)
38. Lu Xu, Hao Li, Wei Lu, and Lidong Bing. 2020. Position-aware tagging for aspect sentiment triplet extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2339–2349, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lu+Xu%2C+Hao+Li%2C+Wei+Lu%2C+and+Lidong+Bing%2E+2020%2E+Position%2Daware+tagging+for+aspect+sentiment+triplet+extraction%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+Processing+) [our card](https://md.research.elamur.ai/free/en/papers/xu-2020-position-aware-tagging-aspect-sentiment/)
39. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Ling… [find](https://scholar.google.com/scholar?q=Linting+Xue%2C+Noah+Constant%2C+Adam+Roberts%2C+Mihir+Kale%2C+Rami+Al%2DRfou%2C+Aditya+Siddhant%2C+Aditya+Barua%2C+and+Colin+Raffel%2E+2021%2E+mT5%3A+A+massively+multilingual+pre%2Dtrained+text%2Dto%2Dtext+transformer%2E+In+Procee) [our card](https://md.research.elamur.ai/free/en/papers/xue-2021-mt5-massively-multilingual-pre-trained/)
40. Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, and Wai Lam. 2021a. Aspect sentiment quad prediction as paraphrase generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9209–9219, Online and Punta Cana, Dominican Republic. Association… [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Yang+Deng%2C+Xin+Li%2C+Yifei+Yuan%2C+Lidong+Bing%2C+and+Wai+Lam%2E+2021a%2E+Aspect+sentiment+quad+prediction+as+paraphrase+generation%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2021-aspect-sentiment-quad-prediction-as/)
41. Wenxuan Zhang, Yue Deng, Bing Liu, Sinno Pan, and Lidong Bing. 2024. Sentiment analysis in the era of large language models: A reality check. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3881–3906, Mexico City, Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Yue+Deng%2C+Bing+Liu%2C+Sinno+Pan%2C+and+Lidong+Bing%2E+2024%2E+Sentiment+analysis+in+the+era+of+large+language+models%3A+A+reality+check%2E+In+Findings+of+the+Association+for+Computational+Linguisti) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2023-sentiment-analysis-era-large-language/)
42. Wenxuan Zhang, Ruidan He, Haiyun Peng, Lidong Bing, and Wai Lam. 2021b. Cross-lingual aspect-based sentiment analysis with aspect term code-switching. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9220–9230, Online and Punta Cana, Dominican Republic… [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Ruidan+He%2C+Haiyun+Peng%2C+Lidong+Bing%2C+and+Wai+Lam%2E+2021b%2E+Cross%2Dlingual+aspect%2Dbased+sentiment+analysis+with+aspect+term+code%2Dswitching%2E+In+Proceedings+of+the+2021+Conference+on+Empirica)
43. Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, and Wai Lam. 2021c. Towards generative aspect-based sentiment analysis. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Shor… [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Xin+Li%2C+Yang+Deng%2C+Lidong+Bing%2C+and+Wai+Lam%2E+2021c%2E+Towards+generative+aspect%2Dbased+sentiment+analysis%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Li)
44. Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, and Wai Lam. 2023. A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges . IEEE Transactions on Knowledge & Data Engineering, 35(11):11019–11038. [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Xin+Li%2C+Yang+Deng%2C+Lidong+Bing%2C+and+Wai+Lam%2E+2023%2E+A+Survey+on+Aspect%2DBased+Sentiment+Analysis%3A+Tasks%2C+Methods%2C+and+Challenges+%2E+IEEE+Transactions+on+Knowledge+%26+Data+Engineering%2C+35%2811)