---
title: "English Prompts are Better for NLI-based Zero-Shot Emotion"
description: "The paper asks which prompt language works best for zero-shot emotion classification of non-English… 55 references, cited by 9 papers here."
authors: ["Patrick Barei\\ss", "Roman Klinger", "Jeremy Barnes"]
year: 2024
venue: "arXiv:2402.03223"
source: "https://arxiv.org/abs/2402.03223"
doi: "10.1145/3589335.3651902"
arxiv: "2402.03223"
licence: "CC BY-SA 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by-sa/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/barei-ss-2024-english-prompts-better-nli-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/barei-ss-2024-english-prompts-better-nli-based/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/10/) / English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts

# English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts

**Authors:** Patrick Barei\\ss, [Roman Klinger](https://md.research.elamur.ai/free/en/authors/roman-klinger/) and [Jeremy Barnes](https://md.research.elamur.ai/free/en/authors/jeremy-barnes/) · **Year:** 2024 · **Venue:** [arXiv:2402.03223](https://md.research.elamur.ai/free/en/venues/acm-web-conference-www/) ([WWW 2024](https://md.research.elamur.ai/free/en/venues/acm-web-conference-www/2024/)) · **Licence:** [CC BY-SA 4.0 (arXiv)](http://creativecommons.org/licenses/by-sa/4.0/)

**Links:** [Publisher's page](https://doi.org/10.1145/3589335.3651902) · [PDF](https://arxiv.org/pdf/2402.03223) · [DOI 10.1145/3589335.3651902](https://doi.org/10.1145/3589335.3651902) · [arXiv 2402.03223](https://arxiv.org/abs/2402.03223) · [OpenAlex](https://openalex.org/W4391591497)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/barei-ss-2024-english-prompts-better-nli-based/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks which prompt language works best for zero-shot emotion classification of non-English text with a multilingual model. Emotion label sets differ by domain, which makes zero-shot labelling attractive, but almost all emotion resources and prompting studies are in English. The authors use the NLI reformulation. Each candidate emotion becomes a hypothesis such as "This text expresses joy", the input text is the premise, and the label whose hypothesis gets the highest entailment wins. The models are not fine-tuned on emotion data. The experiment crosses four factors: 3 emotion corpora covering 18 languages, 7 prompt types taken from Plaza-del Arco et al., and 6 multilingual NLI models from HuggingFace. Each prompt is either kept in English or machine-translated with Google Translate into the language of the data. English prompts are consistently better, even for languages typologically far from English. The ranking of prompt types stays stable across languages, and the pattern holds across models. The one partial exception is the single model fine-tuned on different NLI data. The result points to an English bias in multilingual models and gives a practical default for cross-lingual prompting.

## Key points
- The setup is NLI-based zero-shot classification. A prompt template with an emotion slot is filled once per candidate label, and the label with maximal entailment is chosen.
- The scale is 3 corpora (including Universal Joy and de/enISEAR), 18 languages (from Bengali and Khmer to Chinese and Tagalog), 7 prompt types and 6 NLI models. The models include XLM-RoBERTa, MiniLMv2, Ernie, XLM-V and mDeBERTa variants.
- The research questions and their answers:
  - RQ1: should the prompt be translated? No, English is better.
  - RQ2: are prompt types stable across data languages? Yes.
  - RQ3: are results consistent across models? Yes.
- The deviating model was the only one trained on different NLI data, which suggests that NLI training data interacts with how well prompts transfer.
- A qualitative study used XLM-RoBERTa on German de/enISEAR with the expr-emo prompt. It found some sentences where the German prompt gave the sensible answer, for example "promoted" labelled joy rather than shame. It also found cases where English prompts seemed less affected by data biases.

## Interesting ideas
- Turning classification into entailment means every label is an explicit, human-readable hypothesis scored against the text, so the label set can change without retraining. This is useful wherever categories differ by domain.
- Hypotheses should be phrased in the language the model knows best, even when the input is in another language, rather than assuming matched languages are optimal.
- A full factorial evaluation (data language × prompt language × prompt type × model) checks whether a ranking of design choices survives changes in the other factors, not just whether one score is high.
- A paired table of the same items under two configurations, split into agreements and disagreements, shows where one setup is right and the other is wrong.
- Domain-specific emotion sets, such as aesthetic or fine-grained ones, are treated as an open slot filled at query time rather than fixed at development time.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): speech-act or irony labels could be checked as explicit hypotheses against a sentence, giving an inspectable reason per label instead of an opaque classifier score.
- **I2** (learn): when using multilingual LLM teachers on non-English or translated material, instructions and label hypotheses could stay in English, with the translated variant tested only as a control.
- **I3** (learn): repair rules or parser configurations could be ranked per treebank and genre to confirm that the ranking is stable before adopting a change.
- **I4** (tree): comparing perceptron parser and gparse outputs item by item on their disagreements would expose systematic error types faster than aggregate LAS.
- **I5** (world): character emotional states in fables could be drawn from an ontology-provided label list and verified per character, which would support "how did X feel" questions in QA.

*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

- [University of Stuttgart](https://md.research.elamur.ai/free/en/universities/university-of-stuttgart/) — University, Stuttgart, Germany · 94 works · 46,609 citations
- [University of the Basque Country](https://md.research.elamur.ai/free/en/universities/university-of-the-basque-country/) — University, Leioa, Spain · 57 works · 16,520 citations
- [University of Bamberg](https://md.research.elamur.ai/free/en/universities/university-of-bamberg/) — University, Bamberg, Germany · 5 works · 65 citations

📚 Shelves (6): [🖥️ 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 · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works

🧭 Topics (4): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works · [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works

## Cite

Cite as: Patrick Barei\\ss, Roman Klinger and Jeremy Barnes. 2024. English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts. arXiv:2402.03223.

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

```bibtex
@misc{bareiss2024english,
  title = {{English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts}},
  author = {Patrick Bareiss, Roman Klinger and Jeremy Barnes},
  year = {2024},
  doi = {10.1145/3589335.3651902},
  eprint = {2402.03223},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3589335.3651902}
}
```

- [← previous Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better](https://md.research.elamur.ai/free/en/papers/liu-2024-does-detectgpt-fully-utilize-perturbation/)
- [next → Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning](https://md.research.elamur.ai/free/en/papers/nacar-2024-enhancing-semantic-similarity-understanding-arabic/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/10/)

## References

55 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Cecilia Ovesdotter Alm, Dan Roth, and Richard Sproat. 2005. [Emotions from Text: Machine Learning for Text-based Emotion Prediction](https://md.research.elamur.ai/free/en/papers/alm-2005-emotions-text-machine-learning-text/). In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Vancouver, British Columbia, Canada, 579–586. https://aclanthology.org/H05-1073 [↗](https://aclanthology.org/H05-1073/)
2. Karin Becker, Viviane P Moreira, and Aline GL dos Santos. 2017. Multilingual emotion classification using supervised learning: Comparative experiments. Information Processing & Management 53, 3 (2017), 684–704. [find](https://scholar.google.com/scholar?q=Karin+Becker%2C+Viviane+P+Moreira%2C+and+Aline+GL+dos+Santos%2E+2017%2E+Multilingual+emotion+classification+using+supervised+learning%3A+Comparative+experiments%2E+Information+Processing+%26+Management+53%2C+3+%282017%29)
3. Federico Bianchi, Debora Nozza, and Dirk Hovy. 2022. XLM-EMO: Multilingual Emotion Prediction in Social Media Text. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis. Association for Computational Linguistics, Dublin, Ireland, 195–203. https://doi.org/10.18653/v1/2022.wassa-1.18 [↗](https://doi.org/10.18653/v1/2022.wassa-1.18)
4. Laura-Ana-Maria Bostan and Roman Klinger. 2018. An Analysis of Annotated Corpora for Emotion Classification in Text. In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics, Santa Fe, New Mexico, USA, 2104–2119. https://aclanthology.org/C18-1179 [↗](https://aclanthology.org/C18-1179/)
5. Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. [A large annotated corpus for learning natural language inference](https://md.research.elamur.ai/free/en/papers/bowman-2015-large-annotated-corpus-learning-natural/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, 632–642. https://doi.org/10.18653/v1/D15-1075 [↗](https://doi.org/10.18653/v1/d15-1075)
6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems 33 (2020), 1877–1901.
7. Xiyao Cheng, Ying Chen, Bixiao Cheng, Shoushan Li, and Guodong Zhou. 2017. An emotion cause corpus for chinese microblogs with multiple-user structures. ACM Transactions on Asian and Low-Resource Language Information Processing 17, 1 (2017), 6:1–6:19. [https://dl.acm.org/citation.cfm?id=3132684](https://dl.acm.org/citation.cfm?id=3132684) [↗](https://dl.acm.org/citation.cfm?id=3132684)
8. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. [Unsupervised Cross-lingual Representation Learning at Scale](https://md.research.elamur.ai/free/en/papers/conneau-2020-unsupervised-cross-lingual-representation-learning/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8440–8451. https://doi.org/10.18653/v1/2020.acl-main.747 [↗](https://doi.org/10.18653/v1/2020.acl-main.747)
9. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. XNLI: Evaluating Cross-lingual Sentence Representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 2475–2485. https://doi.org/10.18653/v1/D18-1269 [↗](https://doi.org/10.18653/v1/d18-1269)
10. Luna De Bruyne. 2023. The Paradox of Multilingual Emotion Detection. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis. Association for Computational Linguistics, Toronto, Canada, 458–466. https://doi.org/10.18653/v1/2023.wassa-1.40 [↗](https://doi.org/10.18653/v1/2023.wassa-1.40)
11. Luna De Bruyne, Pranaydeep Singh, Orphee De Clercq, Els Lefever, and Veronique Hoste. 2022. How Language-Dependent is Emotion Detection? Evidence from Multilingual BERT. In Proceedings of the The 2nd Workshop on Multi-lingual Representation Learning (MRL). Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Hybrid), 76–85. https://doi.org/10.18653/v1/2022. mrl-1.7 [↗](https://doi.org/10.18653/v1/2022)
12. Julen Etxaniz, Gorka Azkune, Aitor Soroa, Oier Lopez de Lacalle, and Mikel Artetxe. 2023. [Do Multilingual Language Models Think Better in English?](https://md.research.elamur.ai/free/en/papers/etxaniz-2024-do-multilingual-language-models-think/) arXiv:2308.01223 [cs.CL] [↗](https://arxiv.org/abs/2308.01223)
13. Jinlan Fu, See-Kiong Ng, and Pengfei Liu. 2022. Polyglot Prompt: Multilingual Multitask Prompt Training. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 9919–9935. https://doi.org/10.18653/v1/ 2022.emnlp-main.674 [↗](https://aclanthology.org/2022.emnlp-main.674/)
14. Vikram Gupta. 2021. [Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Training](https://md.research.elamur.ai/free/en/papers/gupta-2021-multilingual-multilabel-emotion-recognition-virtual/). In Proceedings of the 1st Workshop on Multilingual Representation Learning. Association for Computational Linguistics, Punta Cana, Dominican Republic, 74–85. https://doi.org/10.18653/v1/2021.mrl-1.7 [↗](https://doi.org/10.18653/v1/2021.mrl-1.7)
15. Shreya Havaldar, Bhumika Singhal, Sunny Rai, Langchen Liu, Sharath Chandra Guntuku, and Lyle Ungar. 2023. [Multilingual Language Models are not Multicultural: A Case Study in Emotion](https://md.research.elamur.ai/free/en/papers/havaldar-2023-multilingual-language-models-are-not/). In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis. Association for Computational Linguistics, Toronto, Canada, 202–214. https://doi.org/10.18653/v1/2023.wassa-1.19 [↗](https://doi.org/10.18653/v1/2023.wassa-1.19)
16. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/). arXiv:2111.09543 [cs.CL] [↗](https://arxiv.org/abs/2111.09543)
17. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [DeBERTa: Decoding-enhanced BERT with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In International Conference on Learning Representations. [https://openreview.net/forum?id=XPZIaotutsD](https://openreview.net/forum?id=XPZIaotutsD) [↗](https://openreview.net/forum?id=XPZIaotutsD)
18. Lianzhe Huang, Shuming Ma, Dongdong Zhang, Furu Wei, and Houfeng Wang. 2022. Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 11488–11497. https://doi.org/10.18653/v1/2022. emnlp-main.790 [↗](https://doi.org/10.18653/v1/2022)
19. Eunseo Jeong, Gyunyeop Kim, and Sangwoo Kang. 2023. Multimodal Prompt Learning in Emotion Recognition Using Context and Audio Information. Mathematics 11, 13 (2023), 2908. [find](https://scholar.google.com/scholar?q=Eunseo+Jeong%2C+Gyunyeop+Kim%2C+and+Sangwoo+Kang%2E+2023%2E+Multimodal+Prompt+Learning+in+Emotion+Recognition+Using+Context+and+Audio+Information%2E+Mathematics+11%2C+13+%282023%29%2C+2908%2E)
20. Hwichan Kim and Mamoru Komachi. 2023. Enhancing Few-shot Cross-lingual Transfer with Target Language Peculiar Examples. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, 747–767. https://doi.org/10.18653/v1/2023.findings-acl.47 [↗](https://doi.org/10.18653/v1/2023.findings-acl.47)
21. Sotiris Lamprinidis, Federico Bianchi, Daniel Hardt, and Dirk Hovy. 2021. Universal Joy A Data Set and Results for Classifying Emotions Across Languages. In Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Association for Computational Linguistics, Online, 62–75. https://aclanthology.org/2021.wassa-1.7 [↗](https://aclanthology.org/2021.wassa-1.7/)
22. Moritz Laurer, Wouter van Atteveldt, Andreu Casas, and Kasper Welbers. 2022. Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI. Political Analysis (2022), 1–33. https://doi.org/10.1017/pan.2023.20 [↗](https://doi.org/10.1017/pan.2023.20)
23. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://md.research.elamur.ai/free/en/papers/li-2017-dailydialog-manually-labelled-multi-turn/). In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Asian Federation of Natural Language Processing, Taipei, Taiwan, 986–995. https://aclanthology.org/I17-1099 [↗](https://aclanthology.org/I17-1099/)
24. Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, and Madian Khabsa. 2023. [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://md.research.elamur.ai/free/en/papers/liang-2023-xlm-v-overcoming-vocabulary-bottleneck/). arXiv e-prints, Article arXiv:2301.10472 (Jan. 2023), arXiv:2301.10472 pages. https://doi.org/10.48550/arXiv.2301.10472 arXiv:2301.10472 [cs.CL] [↗](https://doi.org/10.48550/arxiv.2301.10472)
25. Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. [Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/papers/liu-2021-pre-train-prompt-predict-systematic/). ACM Comput. Surv. 55, 9, Article 195 (jan 2023), 35 pages. https://doi.org/10.1145/3560815 [↗](https://doi.org/10.1145/3560815)
26. Rada Mihalcea and Carlo Strapparava. 2012. Lyrics, Music, and Emotions. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, Jeju Island, Korea, 590–599. https://www.aclweb.org/anthology/D12-1054 [↗](https://aclanthology.org/D12-1054/)
27. George A. Miller. 1994. [WordNet: A Lexical Database for English](https://md.research.elamur.ai/free/en/papers/miller-1994-wordnet/). In Human Language Technology: Proceedings of a Workshop held at Plainsboro, New Jersey, March 8-11, 1994. https://aclanthology.org/H94-1111 [↗](https://aclanthology.org/H94-1111/)
28. Saif Mohammad. 2012. [#Emotional Tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2012-emotional-tweets/). In *SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012). Association for Computational Linguistics, Montréal, Canada, 246–255. https://www.aclweb.org/anthology/S12-1033 [↗](https://aclanthology.org/S12-1033/)
29. Saif Mohammad and Felipe Bravo-Marquez. 2017. [Emotion Intensities in Tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2017-emotion-intensities-tweets/). In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017). Association for Computational Linguistics, Vancouver, Canada, 65–77. https://doi.org/10.18653/v1/S17-1007 [↗](https://doi.org/10.18653/v1/s17-1007)
30. Saif Mohammad and Peter D. Turney. 2012. Crowdsourcing a Word-Emotion Association Lexicon. Computational Intelligence 29, 3 (2012). https://doi.org/10. 1111/j.1467-8640.2012.00460.x [↗](https://doi.org/10)
31. Ercong Nie, Sheng Liang, Helmut Schmid, and Hinrich Schütze. 2023. Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, 8320–8340. https://doi.org/10.18653/v1/ 2023.findings-acl.528 [↗](https://aclanthology.org/2023.findings-acl.528/)
32. Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, and Douwe Kiela. 2020. [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://md.research.elamur.ai/free/en/papers/nie-2020-adversarial-nli-new-benchmark-natural/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 4885–4901. https://doi.org/10.18653/v1/2020.acl-main.441 [↗](https://doi.org/10.18653/v1/2020.acl-main.441)
33. Emily Öhman, Marc Pàmies, Kaisla Kajava, and Jörg Tiedemann. 2020. XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Barcelona, Spain (Online), 6542–6552. https://doi.org/10.18653/v1/2020.coling-main.575 [↗](https://doi.org/10.18653/v1/2020.coling-main.575)
34. Flor Miriam Plaza-del Arco, María-Teresa Martín-Valdivia, and Roman Klinger. 2022. Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 6805–6817. https://aclanthology.org/2022.coling-1.592 [↗](https://aclanthology.org/2022.coling-1.592/)
35. Flor Miriam Plaza del Arco, Carlo Strapparava, L. Alfonso Urena Lopez, and Maite Martin. 2020. EmoEvent: A Multilingual Emotion Corpus based on different Events. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 1492– 1498. https://aclanthology.org/2020.lrec-1.186 English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts [↗](https://aclanthology.org/2020.lrec-1.186/)
36. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). J. Mach. Learn. Res. 21, 1, Article 140 (jan 2020), 67 pages.
37. K R Scherer and H G Wallbott. 1994. Evidence for universality and cultural variation of differential emotion response patterning. Journal of personality and social psychology 66, 2 (Feb. 1994), 310–328. https://doi.org/10.1037//0022-3514.66.2.310 [↗](https://doi.org/10.1037//0022-3514.66.2.310)
38. Timo Schick and Hinrich Schütze. 2021. [Few-Shot Text Generation with Natural Language Instructions](https://md.research.elamur.ai/free/en/papers/schick-2021-few-shot-text-generation-natural/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 390–402. https://doi.org/10.18653/v1/2021.emnlp-main.32 [↗](https://doi.org/10.18653/v1/2021.emnlp-main.32)
39. Timo Schick and Hinrich Schütze. 2021. [It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/schick-2021-it-s-not-just-size/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 2339–2352. https://doi.org/10.18653/v1/2021.naacl-main.185 [↗](https://doi.org/10.18653/v1/2021.naacl-main.185)
40. Thomas Schmidt, Katrin Dennerlein, and Christian Wolff. 2021. Emotion Classification in German Plays with Transformer-based Language Models Pretrained on Historical and Contemporary Language. In Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. Association for Computational Linguistics, Punta Cana, Dominican Republic (online), 67–79. https://doi.org/10.18653/v1/2021.latechclfl-1.8 [↗](https://doi.org/10.18653/v1/2021.latechclfl-1.8)
41. Damien Sileo. 2023. tasksource: A Dataset Harmonization Framework for Streamlined NLP Multi-Task Learning and Evaluation. arXiv:2301.05948 [cs.CL] [↗](https://arxiv.org/abs/2301.05948)
42. Yisheng Song, Ting Wang, Puyu Cai, Subrota K Mondal, and Jyoti Prakash Sahoo. 2023. A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities. Comput. Surveys (2023). https://doi.org/10.1145/ 3582688 [↗](https://doi.org/10.1145/)
43. Chi Sun, Xipeng Qiu, Yige Xu, and Xuanjing Huang. 2019. [How to Fine-Tune BERT for Text Classification?](https://md.research.elamur.ai/free/en/papers/sun-2019-fine-tune-bert-text-classification/). In Chinese Computational Linguistics, Maosong Sun, Xuanjing Huang, Heng Ji, Zhiyuan Liu, and Yang Liu (Eds.). Springer International Publishing, Cham, 194–206. https://doi.org/10.1007/978-3-030-32381-3_16 [↗](https://doi.org/10.1007/978-3-030-32381-3_16)
44. Enrica Troiano, Sebastian Padó, and Roman Klinger. 2019. Crowdsourcing and Validating Event-focused Emotion Corpora for German and English. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 4005–4011. https://doi.org/10.18653/v1/P19-1391 [↗](https://doi.org/10.18653/v1/p19-1391)
45. Lifu Tu, Caiming Xiong, and Yingbo Zhou. 2022. Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2022. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 5478–5485. https://doi.org/10.18653/v1/2022.findings-emnlp.401 [↗](https://doi.org/10.18653/v1/2022.findings-emnlp.401)
46. Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, and Furu Wei. 2021. MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pre-trained Transformers. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Online, 2140–2151. https://doi.org/10.18653/v1/2021.findings-acl.188 [↗](https://doi.org/10.18653/v1/2021.findings-acl.188)
47. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://md.research.elamur.ai/free/en/papers/williams-2018-broad-coverage-challenge-corpus-sentence/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, Louisiana, 1112–1122. https://doi.org/10.18653/v1/N18-1101 [↗](https://doi.org/10.18653/v1/n18-1101)
48. Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://md.research.elamur.ai/free/en/papers/yang-2019-xlnet-generalized-autoregressive-pretraining-language/). In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. [https://proceedings.neurips.cc/paper_files/paper/2019/](https://proceedings.neurips.cc/paper_files/paper/2019/) file/dc6a7e655d7e5840e66733e9ee67cc69-Paper.pdf [↗](https://proceedings.neurips.cc/paper_files/paper/2019/)
49. Jingjie Yi, Deqing Yang, Siyu Yuan, Kaiyan Cao, Zhiyao Zhang, and Yanghua Xiao. 2022. Contextual Information and Commonsense Based Prompt for Emotion Recognition in Conversation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 707–723. https://doi.org/10. 1007/978-3-031-26390-3_41 [↗](https://doi.org/10)
50. Wenpeng Yin, Jamaal Hay, and Dan Roth. 2019. [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://md.research.elamur.ai/free/en/papers/yin-2019-benchmarking-zero-shot-text-classification/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 3914– 3923. https://doi.org/10.18653/v1/D19-1404 [↗](https://doi.org/10.18653/v1/d19-1404)
51. Zhengyan Zhang, Xu Han, Zhiyuan Liu, Xin Jiang, Maosong Sun, and Qun Liu. 2019. ERNIE: Enhanced Language Representation with Informative Entities. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 1441–1451. https://doi.org/10.18653/v1/P19-1139 [↗](https://doi.org/10.18653/v1/p19-1139)
52. Jinming Zhao, Ruichen Li, Qin Jin, Xinchao Wang, and Haizhou Li. 2022. Memo-bert: Pre-training model with prompt-based learning for multimodal emotion recognition. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4703–4707. [https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9746910](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9746910) [↗](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9746910)
53. Mengjie Zhao and Hinrich Schütze. 2021. Discrete and Soft Prompting for Multilingual Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 8547–8555. https://doi.org/10.18653/v1/ 2021.emnlp-main.672 [↗](https://aclanthology.org/2021.emnlp-main.672/)
54. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2023. [A Survey of Large Language Models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv:2303.18223 [cs.CL] [↗](https://arxiv.org/abs/2303.18223)
55. Liu Zhuang, Lin Wayne, Shi Ya, and Zhao Jun. 2021. [A Robustly Optimized BERT Pre-training Approach with Post-training](https://md.research.elamur.ai/free/en/papers/zhuang-2021-robustly-optimized-bert-pre-training/). In Proceedings of the 20th Chinese National Conference on Computational Linguistics. Chinese Information Processing Society of China, Huhhot, China, 1218–1227. https://aclanthology.org/2021.ccl-1.108 [↗](https://aclanthology.org/2021.ccl-1.108/)

*Updated 2 November 2026*